Elamur Research⌕
☰
home / papers / 2026 / Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

Paper · 2026 · Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu et al.

Summary

Multimodal foundation models such as VLMs, DMs, LLMs, and AFMs can absorb private, copyrighted, biased, or harmful associations from web-scale training data. Retraining them after a deletion request or policy change is usually too costly. Removing a single concept is also hard because knowledge is spread across shared cross-modal representations. This survey reviews multimodal unlearning across image, text, video, and audio.

Earlier surveys mostly focus on one modality or sort methods by optimization objective. This one instead uses a system-first taxonomy. Its top-level split is by forgetting scope (instance-level vs. concept-level). Within each scope, methods are grouped by where in the pipeline they intervene and through which control pathway. The authors also give a formal setup: a forget/retain objective, an (ε, δ) closeness criterion relative to retraining inspired by differential privacy, and model-specific formulations for VLMs and diffusion models.

The framework makes trade-offs comparable across models: deletion strength, utility retention, efficiency, reversibility, and robustness. It also points to open problems in evaluation reliability, adversarial reactivation of forgotten content, and deployment.

Key points

  • Five intervention stages: data-side interventions, training-time edits, architecture-constrained methods, training-free edits, and decoding-time control. Example methods include SalUn, MultiDelete, CleanCLIP, Task Arithmetic, NegMerge, Safe-CLIP, SAFREE, and SteerDiff.
  • Unlearning is framed as approximating a model retrained on the retained data D_r. A two-sided (ε, δ) bound measures closeness, and ε = δ = 0 corresponds to exact retraining.
  • Diffusion-model unlearning is described through three routes:
    • teacher-guided denoising losses,
    • low-rank or sparse cross-attention edits,
    • sampling-time steering without weight changes, such as negative prompts or reduced guidance.
  • The survey is compared against six earlier surveys (2023–2025) on modality coverage and on whether they use a system-first taxonomy. It positions itself as covering text, image, video, and audio.
  • A curated repository, Awesome-Multimodal-Unlearning, is released. The authors state that audio and video unlearning remain underexplored, and that time-series, tabular, and sensor data are outside the survey's scope.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of North Carolina at Chapel HillChapel Hill · United States67 works · 16,474 citations🎓University of Maryland, Baltimore CountyBaltimore · United States14 works · 915 citations

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 3Research subjects and languages the work is about.Evaluation & benchmarks · 1,220 worksVision & language · 657 worksSpeech & spoken language · 480 works

Cite

Cite as Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu and Vaidehi Patil. 2026. Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1379

@inproceedings{sarwar2026multimodal,
  title = {{Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks}},
  author = {Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu and Vaidehi Patil},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1379},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1379}
}

References

198 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Shristi Das Biswas, Arani Roy, and Kaushik Roy. 2025. Cure: Concept unlearning via orthogonal representation editing in diffusion models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  2. Andrea Agostinelli, Timo I Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, and 1 others. 2023. Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325. — [arXiv:2301.11325](https://arxiv.org/abs/2301.11325) find
  3. Ibrahim Alabdulmohsin, Xiao Wang, Andreas Peter Steiner, Priya Goyal, Alexander D’Amour, and Xiaohua Zhai. 2024. Clip the bias: How useful is balancing data in multimodal learning? In The Twelfth International Conference on Learning Representations. find
  4. Alberto Blanco-Justicia, Najeeb Jebreel, Benet Manzanares-Salor, David Sánchez, Josep Domingo-Ferrer, Guillem Collell, and Kuan Eeik Tan. 2025. Digital forgetting in large language models: A survey of unlearning methods. Artificial Intelligence Review. find
  5. Lukas Bossard, Matthieu Guillaumin, and Luc Van Gool. 2014. Food-101–mining discriminative components with random forests. In European conference on computer vision. find
  6. Lucas Bourtoule, Varun Chandrasekaran, Christopher A Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot. 2021. Machine unlearning. In 2021 IEEE Symposium on Security and Privacy (SP). find
  7. Anh Tuan Bui, Khanh Doan, Trung Le, Paul Montague, Tamas Abraham, and Dinh Phung. 2025. Hiding and recovering knowledge in text-to-image diffusion models via learnable prompts. In ICLR Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy. find
  8. Burak. 2020. Pins face recognition. https://www.kaggle.com/datasets/hereisburak/ pins-face-recognition. Kaggle dataset. ↗
  9. Zikui Cai, Yaoteng Tan, and M Salman Asif. 2025. Targeted unlearning with single layer unlearning gradient. In Forty-second International Conference on Machine Learning. find
  10. Qiong Cao, Li Shen, Weidi Xie, Omkar M Parkhi, and Andrew Zisserman. 2018. Vggface2: A dataset for recognising faces across pose and age. In 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018). find
  11. Yinzhi Cao and Junfeng Yang. 2015. Towards making systems forget with machine unlearning. In 2015 IEEE symposium on security and privacy. find
  12. Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, and Florian Tramer. 2022. Membership inference attacks from first principles. In 2022 IEEE symposium on security and privacy. find
  13. Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael Abu-Ghazaleh, M Salman Asif, Yue Dong, Amit Roy-Chowdhury, and Chengyu Song. 2024. Can textual unlearning solve cross-modality safety alignment? In Findings of the Association for Computational Linguistics: EMNLP 2024. find
  14. Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, and Xuming Hu. 2025a. Safeeraser: Enhancing safety in multimodal large language models through multimodal machine unlearning. arXiv preprint arXiv:2502.12520. find
  15. Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, and 1 others. 2022. Wavlm: Large-scale self-supervised pre-training for full stack speech processing. IEEE Journal of Selected Topics in Signal Processing. find
  16. Siyi Chen, Yimeng Zhang, Sijia Liu, and Qing Qu. 2025b. The dual power of interpretable token embeddings: Jailbreaking attacks and defenses for diffusion model unlearning. arXiv preprint arXiv:2504.21307. — [arXiv:2504.21307](https://arxiv.org/abs/2504.21307) find
  17. Tianqi Chen, Shujian Zhang, and Mingyuan Zhou. 2025c. Score forgetting distillation: A swift, data-free method for machine unlearning in diffusion models. In The Thirteenth International Conference on Learning Representations. find
  18. Yiwei Chen, Yuguang Yao, Yihua Zhang, Bingquan Shen, Gaowen Liu, and Sijia Liu. 2025d. Safety mirage: How spurious correlations undermine vlm safety fine-tuning. arXiv preprint arXiv:2503.11832. — [arXiv:2503.11832](https://arxiv.org/abs/2503.11832) find
  19. Jiali Cheng and Hadi Amiri. 2024a. Mu-bench: A multitask multimodal benchmark for machine unlearning. arXiv preprint arXiv:2406.14796. — [arXiv:2406.14796](https://arxiv.org/abs/2406.14796) find
  20. Jiali Cheng and Hadi Amiri. 2024b. Multidelete for multimodal machine unlearning. In European Conference on Computer Vision. find
  21. Jiali Cheng and Hadi Amiri. 2025. Speech unlearning. arXiv preprint arXiv:2506.00848. — [arXiv:2506.00848](https://arxiv.org/abs/2506.00848) find
  22. Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919.
  23. Mircea Cimpoi, Subhransu Maji, Iasonas Kokkinos, Sammy Mohamed, and Andrea Vedaldi. 2014. Describing textures in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition. find
  24. Bartosz Cywiński and Kamil Deja. 2025. Saeuron: Interpretable concept unlearning in diffusion models with sparse autoencoders. In Forty-second International Conference on Machine Learning. find
  25. Juntao Dai, Tianle Chen, Xuyao Wang, Ziran Yang, Taiye Chen, Jiaming Ji, and Yaodong Yang. 2024. Safesora: Towards safety alignment of text2video generation via a human preference dataset. Advances in Neural Information Processing Systems. find
  26. Zheng Dai and David K Gifford. 2023. Training data attribution for diffusion models. arXiv preprint arXiv:2306.02174. — [arXiv:2306.02174](https://arxiv.org/abs/2306.02174) find
  27. Pucheng Dang, Xing Hu, Dong Li, Rui Zhang, Qi Guo, and Kaidi Xu. 2025a. Diffzoo: A purely query-based black-box attack for red-teaming text-to-image generative model via zeroth order optimization. In Findings of the Association for Computational Linguistics: NAACL 2025. find
  28. Yizhou Dang, Yuting Liu, Enneng Yang, Guibing Guo, Linying Jiang, Jianzhe Zhao, and Xingwei Wang. 2025b. Efficient and adaptive recommendation unlearning: A guided filtering framework to erase outdated preferences. ACM Transactions on Information Systems. find
  29. Edoardo De Matteis, Matteo Migliarini, Alessio Sampieri, Indro Spinelli, and Fabio Galasso. 2025. Human motion unlearning. arXiv preprint arXiv:2503.18674. — [arXiv:2503.18674](https://arxiv.org/abs/2503.18674) find
  30. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. find
  31. Yi Ding, Lijun Li, Bing Cao, and Jing Shao. 2025. Rethinking bottlenecks in safety fine-tuning of vision language models. arXiv preprint arXiv:2501.18533. — [arXiv:2501.18533](https://arxiv.org/abs/2501.18533) find
  32. Jesse Dodge, Taylor Prewitt, Remi Tachet des Combes, Erika Odmark, Roy Schwartz, Emma Strubell, Alexandra Sasha Luccioni, Noah A Smith, Nicole DeCario, and Will Buchanan. 2022. Measuring the carbon intensity of ai in cloud instances. In Proceedings of the 2022 ACM conference on fairness, accountabil… find
  33. Chongyang Gao, Lixu Wang, Kaize Ding, Chenkai Weng, Xiao Wang, and Qi Zhu. 2025a. On large language model continual unlearning. In The Thirteenth International Conference on Learning Representations. find
  34. Hongcheng Gao, Tianyu Pang, Chao Du, Taihang Hu, Zhijie Deng, and Min Lin. 2025b. Meta-unlearning on diffusion models: Preventing relearning unlearned concepts. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  35. Alexey Dontsov, Dmitrii Korzh, Alexey Zhavoronkin, Boris Mikheev, Denis Bobkov, Aibek Alanov, Oleg Y Rogov, Ivan Oseledets, and Elena Tutubalina. 2024. Clear: Character unlearning in textual and visual modalities. arXiv preprint arXiv:2410.18057. find
  36. Jiahui Geng, Qing Li, Herbert Woisetschlaeger, Zongxiong Chen, Fengyu Cai, Yuxia Wang, Preslav Nakov, Hans-Arno Jacobsen, and Fakhri Karray. 2025. A comprehensive survey of machine unlearning techniques for large language models. arXiv preprint arXiv:2503.01854. — [arXiv:2503.01854](https://arxiv.org/abs/2503.01854) find
  37. Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. 2006. Calibrating noise to sensitivity in private data analysis. In Theory of Cryptography: Third Theory of Cryptography Conference, TCC 2006, New York, NY, USA, March 4-7, 2006. Proceedings 3. find
  38. Antonio Ginart, Melody Guan, Gregory Valiant, and James Y Zou. 2019. Making ai forget you: Data deletion in machine learning. Advances in neural information processing systems. find
  39. Simone Facchiano, Stefano Saravalle, Matteo Migliarini, Edoardo De Matteis, Alessio Sampieri, Andrea Pilzer, Emanuele Rodolà, Indro Spinelli, Luca Franco, and Fabio Galasso. 2025. Video unlearning via low-rank refusal vector. arXiv preprint arXiv:2506.07891. — [arXiv:2506.07891](https://arxiv.org/abs/2506.07891) find
  40. Chongyu Fan, Jiancheng Liu, Yihua Zhang, Eric Wong, Dennis Wei, and Sijia Liu. 2023. Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation. In The Twelfth International Conference on Learning Representations. find
  41. XiaoHua Feng, Yuyuan Li, Chaochao Chen, Li Zhang, Longfei Li, Jun Zhou, and Xiaolin Zheng. 2025a. Controllable Unlearning for Image-to-Image Generative Models via ε-Constrained Optimization. In The Thirteenth International Conference on Learning Representations. find
  42. Xiaohua Feng, Jiaming Zhang, Fengyuan Yu, Chengye Wang, Li Zhang, Kaixiang Li, Yuyuan Li, Chaochao Chen, and Jianwei Yin. 2025b. A survey on generative model unlearning: Fundamentals, taxonomy, evaluation, and future direction. arXiv preprint arXiv:2507.19894. — [arXiv:2507.19894](https://arxiv.org/abs/2507.19894) find
  43. Aditya Golatkar, Alessandro Achille, Luca Zancato, Yu-Xiang Wang, Ashwin Swaminathan, and Stefano Soatto. 2024. Cpr: Retrieval augmented generation for copyright protection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. find
  44. Eric Goldman. 2020. An introduction to the california consumer privacy act (ccpa). Santa Clara Univ. Legal Studies Research Paper. find
  45. Yichen Gong, Delong Ran, Jinyuan Liu, Conglei Wang, Tianshuo Cong, Anyu Wang, Sisi Duan, and Xiaoyun Wang. 2025. Figstep: Jailbreaking large vision-language models via typographic visual prompts. In Proceedings of the AAAI Conference on Artificial Intelligence. find
  46. Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. 2017. Making the v in vqa matter: Elevating the role of image understanding in visual question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition.
  47. Chuan Guo, Tom Goldstein, Awni Hannun, and Laurens Van Der Maaten. 2020. Certified data removal from machine learning models. In International Conference on Machine Learning. find
  48. Rohit Gandikota, Joanna Materzynska, Jaden Fiotto-Kaufman, and David Bau. 2023. Erasing concepts from diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  49. Danna Gurari, Qing Li, Abigale J Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, and Jeffrey P Bigham. 2018. Vizwiz grand challenge: Answering visual questions from blind people. In Proceedings of the IEEE conference on computer vision and pattern recognition. find
  50. Rohit Gandikota, Hadas Orgad, Yonatan Belinkov, Joanna Materzyńska, and David Bau. 2024. Unified concept editing in diffusion models. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. find
  51. Haochen Han, Alex Jinpeng Wang, Peijun Ye, and Fangming Liu. 2025a. Unlearning the noisy correspondence makes clip more robust. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  52. Xiaoxuan Han, Songlin Yang, Wei Wang, Yang Li, and Jing Dong. 2024. Probing unlearned diffusion models: A transferable adversarial attack perspective. arXiv preprint arXiv:2404.19382. — [arXiv:2404.19382](https://arxiv.org/abs/2404.19382) find
  53. Xiaoxuan Han, Songlin Yang, Wei Wang, Yang Li, and Jing Dong. 2025b. Adaptive median smoothing: Adversarial defense for unlearned text-to-image diffusion models at inference time. In Forty-second International Conference on Machine Learning. find
  54. Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
  55. Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems. find
  56. Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems. find
  57. Yupeng Hou, Jiacheng Li, Zhankui He, An Yan, Xiusi Chen, and Julian McAuley. 2024. Bridging language and items for retrieval and recommendation. arXiv preprint arXiv:2403.03952. — [arXiv:2403.03952](https://arxiv.org/abs/2403.03952) find
  58. Jiahao Huo, Yibo Yan, Xu Zheng, Yuanhuiyi Lyu, Xin Zou, Zhihua Wei, and Xuming Hu. 2025. Mmunlearner: Reformulating multimodal machine unlearning in the era of multimodal large language models. In Findings of the Association for Computational Linguistics: ACL 2025. find
  59. Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2023. Editing models with task arithmetic. In The Eleventh International Conference on Learning Representations.
  60. Abha Jha, Ashwath Vaithinathan Aravindan, Matthew Salaway, Atharva Sandeep Bhide, and Duygu Nur Yaldiz. 2025. Backdoor defense in diffusion models via spatial attention unlearning. arXiv preprint arXiv:2504.18563. — [arXiv:2504.18563](https://arxiv.org/abs/2504.18563) find
  61. Jinghan Jia, Jiancheng Liu, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, and Sijia Liu. 2023. Model sparsity can simplify machine unlearning. Advances in Neural Information Processing Systems. find
  62. Er Jin, Yang Zhang, Yongli Mou, Yanfei Dong, Stefan Decker, Kenji Kawaguchi, and Johannes Stegmaier. 2025. Unconsciously forget: Mitigating memorization; without knowing what is being memorized. arXiv preprint arXiv:2512.09687. — [arXiv:2512.09687](https://arxiv.org/abs/2512.09687) find
  63. Jeremy Howard. 2019. Imagenette: A smaller subset of 10 easily classified classes from imagenet. https://github.com/fastai/imagenette. GitHub repository. ↗
  64. Kimmo Karkkainen and Jungseock Joo. 2021. Fairface: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision. find
  65. Xuhao Hu, Dongrui Liu, Hao Li, Xuan-Jing Huang, and Jing Shao. 2025. Vlsbench: Unveiling visual leakage in multimodal safety. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics.
  66. Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2018. Progressive growing of gans for improved quality, stability, and variation. In International Conference on Learning Representations. find
  67. Huaxi Huang, Xin Yuan, Qiyu Liao, Dadong Wang, and Tongliang Liu. 2024a. Enhancing user-centric privacy protection: An interactive framework through diffusion models and machine unlearning. arXiv preprint arXiv:2409.03326. — [arXiv:2409.03326](https://arxiv.org/abs/2409.03326) find
  68. Kai Huang, Haoming Wang, and Wei Gao. 2024b. Freezeasguard: Mitigating illegal adaptation of diffusion models via selective tensor freezing. arXiv preprint arXiv:2405.17472. — [arXiv:2405.17472](https://arxiv.org/abs/2405.17472) find
  69. Rongjie Huang, Mingze Li, Dongchao Yang, Jiatong Shi, Xuankai Chang, Zhenhui Ye, Yuning Wu, Zhiqing Hong, Jiawei Huang, Jinglin Liu, and 1 others. 2024c. Audiogpt: Understanding and generating speech, music, sound, and talking head. In Proceedings of the AAAI Conference on Artificial Intelligence. find
  70. Drew A Hudson and Christopher D Manning. 2019. Gqa: A new dataset for real-world visual reasoning and compositional question answering. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
  71. Tero Karras, Samuli Laine, and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. find
  72. Tatsuki Kawakami, Kazuki Egashira, Atsuyuki Miyai, Go Irie, and Kiyoharu Aizawa. 2025. Pulse: Practical evaluation scenarios for large multimodal model unlearning. arXiv preprint arXiv:2507.01271. — [arXiv:2507.01271](https://arxiv.org/abs/2507.01271) find
  73. Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Fei-Fei Li. 2011. Novel dataset for fine-grained image categorization: Stanford dogs. In Proc. CVPR workshop on fine-grained visual categorization (FGVC). find
  74. Hyoseo Kim, Dongyoon Han, and Junsuk Choe. 2024a. Negmerge: Consensual weight negation for strong machine unlearning. In Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning. find
  75. Jinju Kim, Taehan Kim, Abdul Waheed, and Rita Singh. 2025a. No encore: Unlearning as opt-out in music generation. arXiv preprint arXiv:2509.06277. — [arXiv:2509.06277](https://arxiv.org/abs/2509.06277) find
  76. Minseon Kim, Hyomin Lee, Boqing Gong, Huishuai Zhang, and Sung Ju Hwang. 2024b. Automatic jailbreaking of the text-to-image generative ai systems. In ICML 2024 Next Generation of AI Safety Workshop. find
  77. Nupur Kumari, Bingliang Zhang, Sheng-Yu Wang, Eli Shechtman, Richard Zhang, and Jun-Yan Zhu. 2023. Ablating concepts in text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  78. Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, and Juho Lee. 2023. Towards safe self-distillation of internet-scale text-to-image diffusion models. arXiv preprint arXiv:2307.05977. — [arXiv:2307.05977](https://arxiv.org/abs/2307.05977) find
  79. Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 2002. Gradient-based learning applied to document recognition. Proceedings of the IEEE. find
  80. Taesoo Kim, Jinju Kim, Dong Chan Kim, Jong Hwan Ko, and Gyeong-Moon Park. 2025b. Do not mimic my voice: Speaker identity unlearning for zero-shot text-to-speech. In ICML 2025 Workshop on Machine Unlearning for Generative AI. find
  81. Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, and Omer Levy. 2023. Pick-a-pic: An open dataset of user preferences for text-to-image generation. Advances in neural information processing systems. find
  82. Myeongseob Ko, Henry Li, Zhun Wang, Jonathan Patsenker, Jiachen Tianhao Wang, Qinbin Li, Ming Jin, Dawn Song, and Ruoxi Jia. 2024. Boosting alignment for post-unlearning text-to-image generative models. Advances in Neural Information Processing Systems. find
  83. Alkis Koudounas, Moreno La Quatra, Lorenzo Vaiani, Luca Colomba, Giuseppe Attanasio, Eliana Pastor, Luca Cagliero, and Elena Baralis. 2023. Italic: An italian intent classification dataset. In INTER-SPEECH. find
  84. Alkis Koudounas, Claudio Savelli, Flavio Giobergia, and Elena Baralis. 2025. “Alexa, can you forget me?” machine unlearning benchmark in spoken language understanding. arXiv preprint arXiv:2505.15700. — [arXiv:2505.15700](https://arxiv.org/abs/2505.15700) find
  85. Boheng Li, Renjie Gu, Junjie Wang, Leyi Qi, Yiming Li, Run Wang, Zhan Qin, and Tianwei Zhang. 2025a. Towards resilient safety-driven unlearning for diffusion models against downstream fine-tuning. arXiv preprint arXiv:2507.16302. — [arXiv:2507.16302](https://arxiv.org/abs/2507.16302) find
  86. Feifei Li, Mi Zhang, Yiming Sun, and Min Yang. 2025b. Detect-and-guide: Self-regulation of diffusion models for safe text-to-image generation via guideline token optimization. In Proceedings of the Computer Vision and Pattern Recognition Conference. find
  87. Gen Li, Yang Xiao, Jie Ji, Kaiyuan Deng, Bo Hui, Linke Guo, and Xiaolong Ma. 2025c. Sculpting memory: Multi-concept forgetting in diffusion models via dynamic mask and concept-aware optimization. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  88. Guihong Li, Hsiang Hsu, Chun-Fu Chen, and Radu Marculescu. 2024a. Machine unlearning for image-to-image generative models. In The Twelfth International Conference on Learning Representations. find
  89. Jiaqi Li, Qianshan Wei, Chuanyi Zhang, Guilin Qi, Miaozeng Du, Yongrui Chen, Sheng Bi, and Fan Liu. 2024b. Single image unlearning: Efficient machine unlearning in multimodal large language models. Advances in Neural Information Processing Systems. find
  90. Felix Koulischer, Johannes Deleu, Gabriel Raya, Thomas Demeester, and Luca Ambrogioni. 2025. Dynamic negative guidance of diffusion models. In The Thirteenth International Conference on Learning Representations. find
  91. Senmao Li, Joost van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang, and Jian Yang. 2024c. Get what you want, not what you don’t: Image content suppression for text-to-image diffusion models. In The Twelfth International Conference on Learning Representations. find
  92. Jonathan Krause, Michael Stark, Jia Deng, and Li Fei-Fei. 2013. 3d object representations for fine-grained categorization. In Proceedings of the IEEE international conference on computer vision workshops. find
  93. Xiang Li, Qianli Shen, Haonan Wang, and Kenji Kawaguchi. 2025d. Loreun: Data itself implicitly provides cues to improve machine unlearning. arXiv preprint arXiv:2507.22499. — [arXiv:2507.22499](https://arxiv.org/abs/2507.22499) find
  94. Alexey Kravets and Vinay P Namboodiri. 2025a. Zero-shot class unlearning in clip with synthetic samples. In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). find
  95. Xinfeng Li, Yuchen Yang, Jiangyi Deng, Chen Yan, Yanjiao Chen, Xiaoyu Ji, and Wenyuan Xu. 2024d. Safegen: Mitigating unsafe content generation in text-to-image models. CoRR. find
  96. Alexey Kravets and Vinay P Namboodiri. 2025b. Zero-shot clip class forgetting via text-image space adaptation. Transactions on Machine Learning Research. find
  97. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Evaluating object hallucination in large vision-language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.
  98. Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Technical report, Department of Computer Science, University of Toronto. Technical Report. find
  99. Siyuan Liang, Kuanrong Liu, Jiajun Gong, Jiawei Liang, Yuan Xun, Ee-Chien Chang, and Xiaochun Cao. 2024a. Unlearning backdoor threats: Enhancing backdoor defense in multimodal contrastive learning via local token unlearning. arXiv preprint arXiv:2403.16257. — [arXiv:2403.16257](https://arxiv.org/abs/2403.16257) find
  100. Siyuan Liang, Mingli Zhu, Aishan Liu, Baoyuan Wu, Xiaochun Cao, and Ee-Chien Chang. 2024b. Badclip: Dual-embedding guided backdoor attack on multimodal contrastive learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. find
  101. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In European conference on computer vision.
  102. Zhiqiu Lin, Deepak Pathak, Baiqi Li, Jiayao Li, Xide Xia, Graham Neubig, Pengchuan Zhang, and Deva Ramanan. 2024. Evaluating text-to-visual generation with image-to-text generation. In European Conference on Computer Vision. find
  103. Chris Liu, Yaxuan Wang, Jeffrey Flanigan, and Yang Liu. 2024a. Large language model unlearning via embedding-corrupted prompts. Advances in Neural Information Processing Systems. find
  104. Hongbin Liu, Wenjie Qu, Jinyuan Jia, and Neil Zhenqiang Gong. 2024b. Pre-trained encoders in self-supervised learning improve secure and privacy-preserving supervised learning. In 2024 IEEE Security and Privacy Workshops (SPW). find
  105. Kuanrong Liu, Siyuan Liang, Jiawei Liang, Pengwen Dai, and Xiaochun Cao. 2024c. Efficient backdoor defense in multimodal contrastive learning: A token-level unlearning method for mitigating threats. arXiv preprint arXiv:2409.19526. — [arXiv:2409.19526](https://arxiv.org/abs/2409.19526) find
  106. Renyang Liu, Guanlin Li, Tianwei Zhang, and See-Kiong Ng. 2025a. Image can bring your memory back: A novel multi-modal guided attack against image generation model unlearning. arXiv preprint arXiv:2507.07139. — [arXiv:2507.07139](https://arxiv.org/abs/2507.07139) find
  107. Shiqi Liu and Yihua Tan. 2024. Unlearning concepts from text-to-video diffusion models. arXiv preprint arXiv:2407.14209. find
  108. Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Yuguang Yao, Chris Yuhao Liu, Xiaojun Xu, Hang Li, and 1 others. 2025b. Rethinking machine unlearning for large language models. Nature Machine Intelligence. find
  109. Xinwei Liu, Xiaojun Jia, Yuan Xun, Siyuan Liang, and Xiaochun Cao. 2024d. Multimodal unlearnable examples: Protecting data against multimodal contrastive learning. In Proceedings of the 32nd ACM International Conference on Multimedia. find
  110. Yixin Liu, Chenrui Fan, Yutong Dai, Xun Chen, Pan Zhou, and Lichao Sun. 2024e. Metacloak: Preventing unauthorized subject-driven text-to-image diffusion-based synthesis via meta-learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  111. Zhe Liu. 2025. Unlearning llm-based speech recognition models. In Proc. find
  112. Zheyuan Liu, Guangyao Dou, Mengzhao Jia, Zhaoxuan Tan, Qingkai Zeng, Yongle Yuan, and Meng Jiang. 2025c. Protecting privacy in multimodal large language models with mllmu-bench. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguist…
  113. Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan, Yijun Tian, and Meng Jiang. 2024f. Machine unlearning in generative ai: A survey. arXiv preprint arXiv:2407.20516. — [arXiv:2407.20516](https://arxiv.org/abs/2407.20516) find
  114. Zheyuan Liu, Guangyao Dou, Xiangchi Yuan, Chunhui Zhang, Zhaoxuan Tan, and Meng Jiang. 2025d. Modality-aware neuron pruning for unlearning in multimodal large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
  115. Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. 2015. Deep learning face attributes in the wild. In Proceedings of the IEEE international conference on computer vision. find
  116. Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems. find
  117. Shilin Lu, Zilan Wang, Leyang Li, Yanzhu Liu, and Adams Wai-Kin Kong. 2024. Mace: Mass concept erasure in diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  118. Rui Ma, Qiang Zhou, Bangjun Xiao, Yizhu Jin, Daquan Zhou, Xiuyu Li, Aishani Singh, Yi Qu, Kurt Keutzer, Xiaodong Xie, and 1 others. 2024. A dataset and benchmark for copyright protection from text-to-image diffusion models. arXiv preprint arXiv:2403.12052. — [arXiv:2403.12052](https://arxiv.org/abs/2403.12052) find
  119. Yingzi Ma, Jiongxiao Wang, Fei Wang, Siyuan Ma, Jiazhao Li, Jinsheng Pan, Xiujun Li, Furong Huang, Lichao Sun, Bo Li, and 1 others. 2025. Benchmarking vision language model unlearning via fictitious facial identity dataset. In The Thirteenth International Conference on Learning Representations. find
  120. Kenneth Marino, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. 2019. Ok-vqa: A visual question answering benchmark requiring external knowledge. In Proceedings of the IEEE/cvf conference on computer vision and pattern recognition. find
  121. Israel Mason-Williams, Jing Han, Helen Yannakoudakis, and Cecilia Mascolo. 2025. Machine unlearning in audio: Bridging the modality gap via the prune and regrow paradigm. find
  122. Saemi Moon, Minjong Lee, Sangdon Park, and Dongwoo Kim. 2025. Holistic unlearning benchmark: A multi-faceted evaluation for text-to-image diffusion model unlearning. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  123. Piyush Nagasubramaniam, Neeraj Karamchandani, Chen Wu, and Sencun Zhu. 2025. Prompting forgetting: Unlearning in gans via textual guidance. arXiv preprint arXiv:2504.01218. — [arXiv:2504.01218](https://arxiv.org/abs/2504.01218) find
  124. Arsha Nagrani, Joon Son Chung, and Andrew Zisserman. 2017. Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612. find
  125. Seth Neel, Aaron Roth, and Saeed Sharifi-Malvajerdi. 2021. Descent-to-delete: Gradient-based methods for machine unlearning. In Algorithmic Learning Theory. find
  126. Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Baolin Wu, Andrew Y Ng, and 1 others. 2011. Reading digits in natural images with unsupervised feature learning. In NIPS workshop on deep learning and unsupervised feature learning. find
  127. Jiadong Pan, Hongcheng Gao, Zongyu Wu, Taihang Hu, Li Su, Qingming Huang, and Liang Li. 2024. Leveraging catastrophic forgetting to develop safe diffusion models against malicious finetuning. Advances in Neural Information Processing Systems. find
  128. Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. 2015. Librispeech: an asr corpus based on public domain audio books. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP). find
  129. Rameswar Panda, Jianming Zhang, Haoxiang Li, Joon-Young Lee, Xin Lu, and Amit K Roy-Chowdhury. 2018. Contemplating visual emotions: Understanding and overcoming dataset bias. In Proceedings of the European Conference on Computer Vision (ECCV). find
  130. Sunghyun Park, Seokeon Choi, Hyoungwoo Park, and Sungrack Yun. 2025. Steering guidance for personalized text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  131. Yong-Hyun Park, Sangdoo Yun, Jin-Hwa Kim, Junho Kim, Geonhui Jang, Yonghyun Jeong, Junghyo Jo, and Gayoung Lee. 2024. Direct unlearning optimization for robust and safe text-to-image models. Advances in Neural Information Processing Systems. find
  132. Shreyansh Pathak, Sonu Shreshtha, Richa Singh, and Mayank Vatsa. 2025. Quantum-inspired audio unlearning: Towards privacy-preserving voice biometrics. arXiv preprint arXiv:2507.22208. — [arXiv:2507.22208](https://arxiv.org/abs/2507.22208) find
  133. Vaidehi Patil, Yi-Lin Sung, Peter Hase, Jie Peng, Tianlong Chen, and Mohit Bansal. 2024. Unlearning sensitive information in multimodal llms: Benchmark and attack-defense evaluation. Transactions on Machine Learning Research. find
  134. Yuang Peng, Yuxin Cui, Haomiao Tang, Zekun Qi, Runpei Dong, Jing Bai, Chunrui Han, Zheng Ge, Xiangyu Zhang, and Shu-Tao Xia. 2025. Dreambench++: A human-aligned benchmark for personalized image generation. In The Thirteenth International Conference on Learning Representations. find
  135. Agnieszka Polowczyk, Alicja Polowczyk, Dawid Malarz, Artur Kasymov, Marcin Mazur, Jacek Tabor, PrzemysĹ Spurek, and 1 others. 2025. Unguide: Learning to forget with lora-guided diffusion models. arXiv preprint arXiv:2508.05755. — [arXiv:2508.05755](https://arxiv.org/abs/2508.05755) find
  136. Samuele Poppi, Tobia Poppi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, and Rita Cucchiara. 2024. Safe-clip: Removing nsfw concepts from vision-and-language models. In Computer Vision – ECCV 2024. find
  137. Jie Ren, Kangrui Chen, Yingqian Cui, Shenglai Zeng, Hui Liu, Yue Xing, Jiliang Tang, and Lingjuan Lyu. 2025. Six-cd: Benchmarking concept removals for text-to-image diffusion models. In Proceedings of the Computer Vision and Pattern Recognition Conference. find
  138. Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2023. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. find
  139. Matan Rusanovsky, Shimon Malnick, Amir Jevnisek, Ohad Fried, and Shai Avidan. 2025. Memories of forgotten concepts. In Proceedings of the Computer Vision and Pattern Recognition Conference. find
  140. Babak Saleh and Ahmed Elgammal. 2015. Large-scale classification of fine-art paintings: Learning the right metric on the right feature. arXiv preprint arXiv:1505.00855. — [arXiv:1505.00855](https://arxiv.org/abs/1505.00855) find
  141. Andrea Schioppa, Emiel Hoogeboom, and Jonathan Heek. 2024. Model integrity when unlearning with t2i diffusion models. arXiv preprint arXiv:2411.02068. — [arXiv:2411.02068](https://arxiv.org/abs/2411.02068) find
  142. Patrick Schramowski, Manuel Brack, Björn Deiseroth, and Kristian Kersting. 2023. Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  143. Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, and 1 others. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information proce…
  144. Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114.
  145. Diana Sousa, André Lamúrias, and Francisco M Couto. 2019. A silver standard corpus of human phenotype-gene relations. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. find
  146. Ayush Sekhari, Jayadev Acharya, Gautam Kamath, and Ananda Theertha Suresh. 2021. Remember what you want to forget: Algorithms for machine unlearning. Advances in Neural Information Processing Systems. find
  147. Christoforos N Spartalis, Theodoros Semertzidis, Petros Daras, and Stratis Gavves. 2025. Unleashing uncertainty: Efficient machine unleanring for generative ai. In ICML 2025 Workshop on Machine Unlearning for Generative AI. find
  148. Marcin Sendera, Łukasz Struski, Kamil Ksi a żek, Kryspin Musiol, Jacek Tabor, and Dawid Rymarczyk. 2025. Semu: Singular value decomposition for efficient machine unlearning. In Forty-second International Conference on Machine Learning. find
  149. Aakash Sen Sharma, Niladri Sarkar, Vikram Chundawat, Ankur A Mali, and Murari Mandal. 2024. Unlearning or concealment? a critical analysis and evaluation metrics for unlearning in diffusion models. arXiv preprint arXiv:2409.05668. — [arXiv:2409.05668](https://arxiv.org/abs/2409.05668) find
  150. Piyush Sharma, Nan Ding, Sebastian Goodman, and Radu Soricut. 2018. Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.
  151. Reza Shirkavand, Peiran Yu, Shangqian Gao, Gowthami Somepalli, Tom Goldstein, and Heng Huang. 2025. Efficient fine-tuning and concept suppression for pruned diffusion models. In Proceedings of the Computer Vision and Pattern Recognition Conference. find
  152. Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2017. Membership inference attacks against machine learning models. In 2017 IEEE symposium on security and privacy.
  153. Nianwen Si, Hao Zhang, Heyu Chang, Wenlin Zhang, Dan Qu, and Weiqiang Zhang. 2023. Knowledge unlearning for llms: Tasks, methods, and challenges. arXiv preprint arXiv:2311.15766. — [arXiv:2311.15766](https://arxiv.org/abs/2311.15766) find
  154. Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, and Kristian Kersting. 2024. Exploiting cultural biases via homoglyphs intext-to-image synthesis. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. find
  155. Alane Suhr, Stephanie Zhou, Ally Zhang, Iris Zhang, Huajun Bai, and Yoav Artzi. 2019. A corpus for reasoning about natural language grounded in photographs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.
  156. Ye Sun, Hao Zhang, Tiehua Zhang, Xingjun Ma, and Yu-Gang Jiang. 2024. Unseg: one universal unlearnable example generator is enough against all image segmentation. In Proceedings of the 38th International Conference on Neural Information Processing Systems. find
  157. Vinith M Suriyakumar, Rohan Alur, Ayush Sekhari, Manish Raghavan, and Ashia C Wilson. 2024. Unstable unlearning: The hidden risk of concept resurgence in diffusion models. arXiv preprint arXiv:2410.08074. — [arXiv:2410.08074](https://arxiv.org/abs/2410.08074) find
  158. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, and 1 others. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805.
  159. Yash Sinha, Murari Mandal, and Mohan Kankanhalli. 2025. Multi-modal recommendation unlearning for legal, licensing, and modality constraints. In Proceedings of the AAAI Conference on Artificial Intelligence. find
  160. Alexander Y Tong, Guillaume Huguet, Amine Natik, Kincaid MacDonald, Manik Kuchroo, Ronald Coifman, Guy Wolf, and Smita Krishnaswamy. 2021. Diffusion earth mover’s distance and distribution embeddings. In International Conference on Machine Learning. find
  161. Justin Solomon, Raif Rustamov, Leonidas Guibas, and Adrian Butscher. 2014. Earth mover’s distances on discrete surfaces. ACM Transactions on Graphics (ToG). find
  162. Thomas Unterthiner, Sjoerd Van Steenkiste, Karol Kurach, Raphaël Marinier, Marcin Michalski, and Sylvain Gelly. 2019. Fvd: A new metric for video generation. find
  163. ICLR 2019 Workshop DeepGenStruct. find
  164. Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402. — [arXiv:1212.0402](https://arxiv.org/abs/1212.0402) find
  165. Paul Voigt and Axel Von dem Bussche. 2017. The eu general data protection regulation (gdpr). A Practical Guide, 1st Ed., Cham: Springer International Publishing. find
  166. Chengye Wang, Yuyuan Li, XiaoHua Feng, Chaochao Chen, Xiaolin Zheng, and Jianwei Yin. 2025a. Umu-bench: Closing the modality gap in multimodal unlearning evaluation. In The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track. find
  167. Peiran Wang, Qiyu Li, Longxuan Yu, Ziyao Wang, Ang Li, and Haojian Jin. 2024. Moderator: Moderating text-to-image diffusion models through fine-grained context-based policies. In Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security. find
  168. Yihan Wang, Yiwei Lu, Guojun Zhang, Franziska Boenisch, Adam Dziedzic, Yaoliang Yu, and Xiao-Shan Gao. 2025b. Muc: Machine unlearning for contrastive learning with black-box evaluation. Transactions on Machine Learning Research. find
  169. Yuan Wang, Ouxiang Li, Tingting Mu, Yanbin Hao, Kuien Liu, Xiang Wang, and Xiangnan He. 2025c. Precise, fast, and low-cost concept erasure in value space: Orthogonal complement matters. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). find
  170. Zhiqi Wang, Chengyu Zhang, Yuetian Chen, Nathalie Baracaldo, Swanand Kadhe, and Lei Yu. 2025d. Membership inference attacks as privacy tools: Reliability, disparity and ensemble. arXiv preprint arXiv:2506.13972. — [arXiv:2506.13972](https://arxiv.org/abs/2506.13972) find
  171. Zijie J Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen Horng Chau. 2023. Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. find
  172. Pete Warden. 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209. find
  173. Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, and Mohit Bansal. 2025a. Medforget: Hierarchy-aware multimodal unlearning testbed for medical ai. arXiv preprint arXiv:2512.09867. find
  174. Jing Wu and Mehrtash Harandi. 2025. Munba: Machine unlearning via nash bargaining. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  175. Yongliang Wu, Shiji Zhou, Mingzhuo Yang, Lianzhe Wang, Heng Chang, Wenbo Zhu, Xinting Hu, Xiao Zhou, and Xu Yang. 2025b. Unlearning concepts in diffusion model via concept domain correction and concept preserving gradient. In Proceedings of the AAAI Conference on Artificial Intelligence. find
  176. Jianxiong Xiao, Krista A Ehinger, James Hays, Antonio Torralba, and Aude Oliva. 2016. Sun database: Exploring a large collection of scene categories. International Journal of Computer Vision. find
  177. Shangyu Xing, Fei Zhao, Zhen Wu, Tuo An, Weihao Chen, Chunhui Li, Jianbing Zhang, and Xinyu Dai. 2024. Efuf: Efficient fine-grained unlearning framework for mitigating hallucinations in multimodal large language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language P… find
  178. Naen Xu, Jinghuai Zhang, Changjiang Li, Zhi Chen, Chunyi Zhou, Qingming Li, Tianyu Du, and Shouling Ji. 2025a. Videoeraser: Concept erasure in text-to-video diffusion models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. find
  179. Zhaopan Xu, Pengfei Zhou, Weidong Tang, Jiaxin Ai, Wangbo Zhao, Kai Wang, Xiaojiang Peng, Wenqi Shao, Hongxun Yao, and Kaipeng Zhang. 2025b. Pebench: A fictitious dataset to benchmark machine unlearning for multimodal large language models. arXiv preprint arXiv:2503.12545. — [arXiv:2503.12545](https://arxiv.org/abs/2503.12545) find
  180. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  181. Jingyuan Yang, Qirui Huang, Tingting Ding, Dani Lischinski, Danny Cohen-Or, and Hui Huang. 2023. Emoset: A large-scale visual emotion dataset with rich attributes. In Proceedings of the IEEE/CVF International Conference on Computer Vision. find
  182. Tianyu Yang, Lisen Dai, Xiangqi Wang, Minhao Cheng, Yapeng Tian, and Xiangliang Zhang. 2025b. Cliperase: Efficient unlearning of visual-textual associations in clip. In Proceedings of the 63rd Annual Meeting of the ACL. find
  183. Yuchen Yang, Bo Hui, Haolin Yuan, Neil Gong, and Yinzhi Cao. 2024. Sneakyprompt: Jailbreaking text-to-image generative models. In 2024 IEEE symposium on security and privacy (SP). find
  184. Yelp Inc. 2023. Yelp open dataset. https://www.kaggle.com/datasets/yelp-dataset/ yelp-dataset. Accessed: 2026-01-01. ↗
  185. Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z Li. 2014. Learning face representation from scratch. arXiv preprint arXiv:1411.7923. — [arXiv:1411.7923](https://arxiv.org/abs/1411.7923) find
  186. Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, and Mohit Bansal. 2025. Safree: Training-free and adaptive guard for safe text-to-image and video generation. In The Thirteenth International Conference on Learning Representations. find
  187. Peter Young, Alice Lai, Micah Hodosh, and Julia Hockenmaier. 2014. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the association for computational linguistics. find
  188. Chaoshuo Zhang, Chenhao Lin, Zhengyu Zhao, Le Yang, Qian Wang, and Chao Shen. 2025a. Concept unlearning by modeling key steps of diffusion process. arXiv preprint arXiv:2507.06526. — [arXiv:2507.06526](https://arxiv.org/abs/2507.06526) find
  189. Gong Zhang, Kai Wang, Xingqian Xu, Zhangyang Wang, and Humphrey Shi. 2024a. Forget-me-not: Learning to forget in text-to-image diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. find
  190. Hongxiang Zhang, Yifeng He, and Hao Chen. 2024b. Steerdiff: Steering towards safe text-to-image diffusion models. arXiv preprint arXiv:2410.02710. — [arXiv:2410.02710](https://arxiv.org/abs/2410.02710) find
  191. Jiaming Zhang, Xingjun Ma, Qi Yi, Jitao Sang, Yu-Gang Jiang, Yaowei Wang, and Changsheng Xu. 2023. Unlearnable clusters: Towards label-agnostic unlearnable examples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  192. Jihai Zhang, Xiang Lan, Xiaoye Qu, Yu Cheng, Mengling Feng, and Bryan Hooi. 2024c. Learning the unlearned: Mitigating feature suppression in contrastive learning. In European Conference on Computer Vision. find
  193. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition. find
  194. Xianren Zhang, Hui Liu, Delvin Ce Zhang, Xianfeng Tang, Qi He, Dongwon Lee, and Suhang Wang. 2025b. Does multimodal large language model truly unlearn? stealthy mllm unlearning attack. arXiv preprint arXiv:2506.17265. — [arXiv:2506.17265](https://arxiv.org/abs/2506.17265) find
  195. Xianren Zhang, Hui Liu, Delvin Ce Zhang, Xianfeng Tang, Qi He, Dongwon Lee, and Suhang Wang. 2025c. Sua: Stealthy multimodal large language model unlearning attack. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. find
  196. Yaobin Zhang, Weihong Deng, Mei Wang, Jiani Hu, Xian Li, Dongyue Zhao, and Dongchao Wen. 2020. Global-local gcn: Large-scale label noise cleansing for face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  197. Yihua Zhang, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Xiaoming Liu, and Sijia Liu. 2024d. Unlearncanvas: A stylized image dataset to benchmark machine unlearning for diffusion models. arXiv preprint arXiv:2402.11846. — [arXiv:2402.11846](https://arxiv.org/abs/2402.11846) find
  198. Yucheng Zhou, Xiang Li, Qianning Wang, and Jianbing Shen. 2024. Visual in-context learning for large vision-language models. In Findings of the Association for Computational Linguistics ACL 2024. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sarwar-2026-multimodal-unlearning-across-vision-language/