Elamur Research⌕
☰
home / papers / 2026 / Ghost in the Shell: Synonym-Aware Logit Shaping Fingerprint for Copyright Protection of Large Vision-Language Models

Ghost in the Shell: Synonym-Aware Logit Shaping Fingerprint for Copyright Protection of Large Vision-Language Models

Paper · 2026 · Xiaofan Zheng, Xinghao Wang and Xiaojun Wan

Summary

The paper addresses ownership verification for Large Vision-Language Models (LVLMs) that may be stolen, modified through fine-tuning or pruning, and served as black-box APIs. Existing fingerprints are mostly backdoor-style: a trigger image forces an abnormal text reply. The authors argue this damages modality alignment. It also creates a trade-off, because strong implants hurt utility while weak ones are easily erased. Their method, SALSF, works in the logits space instead of the visible output. An auxiliary LLM proposes low-probability synonyms of the model's top-1 token, with anchors restricted to nouns. Training then raises the combined probability of this synonym cluster well above its natural level, while the top-1 token and its probability stay roughly fixed. As a result, greedy outputs look unchanged to users. The owner can still detect the fingerprint statistically, either from API logprobs or through repeated sampling. Experiments show that multimodal performance is preserved and that the fingerprint survives fine-tuning, pruning and model merging better than baselines. This makes the work a practical option for protecting the IP of open LVLMs.

Key points

  • Fingerprint verification relies on the elevated joint probability of semantically coherent long-tail synonym clusters, not on one-to-one trigger-output mappings.
  • In a model-merging attack, the baselines IF and RNA fall to nearly 0% fingerprint success rate (FSR) once the merging coefficient λ exceeds 0.4. SALSF still keeps 23% FSR at λ = 0.8.
  • The full SALSF reaches 82% FSR after fine-tuning on Visual7W and 89% after ST-VQA, with 57.6% accuracy on SEED-Bench as the harmlessness measure.
  • The ablations tested four removals: top-1 probability locking, the synonym mechanism, long-tail filtering, and the noun-only restriction.
    • Dropping top-1 locking or the synonym mechanism lowers SEED-Bench accuracy.
    • Larger synonym sets k raise FSR up to a plateau, but an overly large k introduces semantic drift and hurts performance.
  • The code is released at github.com/qingpingwan/SALSF. Robustness under knowledge distillation has not been tested yet.

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

🎓Peking UniversityBeijing · China315 works · 43,268 citations🎓Xi'an Jiaotong UniversityXi'an · China42 works · 36,431 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksComputer Vision and Pattern Recognition · 3,486 worksHardware and Architecture · 167 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,894 worksVision & language · 811 works

Cite

Cite as Xiaofan Zheng, Xinghao Wang and Xiaojun Wan. 2026. Ghost in the Shell: Synonym-Aware Logit Shaping Fingerprint for Copyright Protection of Large Vision-Language Models. 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.273

@inproceedings{zheng2026ghost,
  title = {{Ghost in the Shell: Synonym-Aware Logit Shaping Fingerprint for Copyright Protection of Large Vision-Language Models}},
  author = {Xiaofan Zheng, Xinghao Wang and Xiaojun Wan},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.273},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.273}
}

References

77 references, 29 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025. Qwen2.5-vl technical report. arXiv preprint arXiv:25…
  3. Hritik Bansal, Nishad Singhi, Yu Yang, Fan Yin, Aditya Grover, and Kai-Wei Chang. 2023. Cleanclip: Mitigating data poisoning attacks in multimodal contrastive learning. Preprint, arXiv:2303.03323. — [arXiv:2303.03323](https://arxiv.org/abs/2303.03323) find
  4. Yi Bin, Wenhao Shi, Yujuan Ding, Zhiqiang Hu, Zheng Wang, Yang Yang, See-Kiong Ng, and Heng Tao Shen. 2024. Gallerygpt: Analyzing paintings with large multimodal models. arXiv preprint arXiv:2408.00491. — [arXiv:2408.00491](https://arxiv.org/abs/2408.00491) find
  5. Ali Furkan Biten, Ruben Tito, Andres Mafla, Lluis Gomez, Marcal Rusinol, CV Jawahar, Ernest Valveny, and Dimosthenis Karatzas. 2019. Scene text visual question answering. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE. find
  6. Jiacheng Cai, Jiahao Yu, Yangguang Shao, and Yuhang Wu. 2025. Utf:undertrained tokens as fingerprints a novel approach to llm identification. Preprint, arXiv:2410.12318. — [arXiv:2410.12318](https://arxiv.org/abs/2410.12318) find
  7. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, and Jifeng Dai. 2023. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. arXiv preprint arXiv:2312.142…
  8. Hongrong Cheng, Miao Zhang, and Javen Qinfeng Shi. 2024. A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):10558–10578. find
  9. Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. Instructblip: Towards general-purpose vision-language models with instruction tuning. Preprint, arXiv:2305.06500.
  10. Anas Awadalla, Irena Gao, Josh Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Gadre, Shiori Sagawa, and 1 others. 2023. Openflamingo: An open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390.
  11. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  12. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. Preprint, arXiv:2308.12966.
  13. Carl Edwards, ChengXiang Zhai, and Heng Ji. 2021. Text2mol: Cross-modal molecule retrieval with natural language queries. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 595–607.
  14. Matthew Finlayson, Xiang Ren, and Swabha Swayamdipta. 2024. Logits of API-protected LLMs leak proprietary information. In First Conference on Language Modeling. find
  15. Qiao Li, Jing Chen, Kun He, Zijun Zhang, Ruiying Du, Jisi She, and Xinxin Wang. 2024a. Model-agnostic adversarial example detection via high-frequency amplification. Computers & Security, 141:103791. find
  16. Anthi Gaidartzi and Irini Stamatoudi. 2025. Authorship and ownership issues raised by ai-generated works: A comparative analysis. Laws, 14(4). find
  17. Yanwei Li, Yuechen Zhang, Chengyao Wang, Zhisheng Zhong, Yixin Chen, Ruihang Chu, Shaoteng Liu, and Jiaya Jia. 2024b. Mini-gemini: Mining the potential of multi-modality vision language models. arXiv preprint arXiv:2403.18814.
  18. Huaizhi Ge, Yiming Li, Qifan Wang, Yongfeng Zhang, and Ruixiang Tang. 2025. When backdoors speak: Understanding llm backdoor attacks through model-generated explanations. Preprint, arXiv:2411.12701. find
  19. Thibaud Gloaguen, Robin Staab, Nikola Jovanović, and Martin Vechev. 2025. Robust llm fingerprinting via domain-specific watermarks. Preprint, arXiv:2505.16723. — [arXiv:2505.16723](https://arxiv.org/abs/2505.16723) find
  20. Jianping Gou, Baosheng Yu, Stephen J. Maybank, and Dacheng Tao. 2021. Knowledge distillation: A survey. International Journal of Computer Vision, 129(6):1789–1819. find
  21. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.
  22. Minghao Hu, Junzhe Wang, Weisen Zhao, Qiang Zeng, and Lannan Luo. 2025. Flowmaltrans: Unsupervised binary code translation for malware detection using flow-adapter architecture. Preprint, arXiv:2508.20212. find
  23. Heng Jin, Chaoyu Zhang, Shanghao Shi, Wenjing Lou, and Y Thomas Hou. 2024. Proflingo: A fingerprinting-based intellectual property protection scheme for large language models. In 2024 IEEE Conference on Communications and Network Security (CNS), pages 1–9. IEEE. find
  24. Hugo Laurençon, Léo Tronchon, Matthieu Cord, and Victor Sanh. 2024. What matters when building vision-language models? Preprint, arXiv:2405.02246.
  25. Bohao Li, Rui Wang, Guangzhi Wang, Yuying Ge, Yixiao Ge, and Ying Shan. 2023a. Seed-bench: Benchmarking multimodal llms with generative comprehension. arXiv preprint arXiv:2307.16125.
  26. Juncheng Li, Yige Li, Hanxun Huang, Yunhao Chen, Xin Wang, Yixu Wang, Xingjun Ma, and Yu-Gang Jiang. 2025. Backdoorvlm: A benchmark for backdoor attacks on vision-language models. Preprint, arXiv:2511.18921. — [arXiv:2511.18921](https://arxiv.org/abs/2511.18921) find
  27. Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023b. BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of…
  28. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023c. Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355.
  29. Siyuan Liang, Jiawei Liang, Tianyu Pang, Chao Du, Aishan Liu, Mingli Zhu, Xiaochun Cao, and Dacheng Tao. 2024. Revisiting backdoor attacks against large vision-language models from domain shift. Preprint, arXiv:2406.18844. — [arXiv:2406.18844](https://arxiv.org/abs/2406.18844) find
  30. Daizong Liu, Mingyu Yang, Xiaoye Qu, Pan Zhou, Yu Cheng, and Wei Hu. 2024a. A survey of attacks on large vision-language models: Resources, advances, and future trends. Preprint, arXiv:2407.07403. — [arXiv:2407.07403](https://arxiv.org/abs/2407.07403) find
  31. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024b. Improved baselines with visual instruction tuning. Preprint, arXiv:2310.03744.
  32. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024c. Llava-next: Improved reasoning, ocr, and world knowledge. find
  33. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. In NeurIPS.
  34. Kang Liu, Brendan Dolan-Gavitt, and Siddharth Garg. 2018. Fine-pruning: Defending against backdooring attacks on deep neural networks. Preprint, arXiv:1805.12185. — [arXiv:1805.12185](https://arxiv.org/abs/1805.12185) find
  35. 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, 35:2507–2521. find
  36. Nicola Lucchi. 2024. Chatgpt: A case study on copyright challenges for generative artificial intelligence systems. European Journal of Risk Regulation, 15(3):602–624. find
  37. Amir M. Mansourian, Rozhan Ahmadi, Masoud Ghafouri, Amir Mohammad Babaei, Elaheh Badali Golezani, Zeynab Yasamani Ghamchi, Vida Ramezanian, Alireza Taherian, Kimia Dinashi, Amirali Miri, and Shohreh Kasaei. 2025. A comprehensive survey on knowledge distillation. Preprint, arXiv:2503.12067. — [arXiv:2503.12067](https://arxiv.org/abs/2503.12067) find
  38. Anshul Nasery, Jonathan Hayase, Creston Brooks, Peiyao Sheng, Himanshu Tyagi, Pramod Viswanath, and Sewoong Oh. 2025. Scalable fingerprinting of large language models. Preprint, arXiv:2502.07760. — [arXiv:2502.07760](https://arxiv.org/abs/2502.07760) find
  39. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8…
  40. 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 ACL.
  41. Wenhao Shi, Zhiqiang Hu, Yi Bin, Junhua Liu, Yang Yang, See-Kiong Ng, Lidong Bing, and Roy Ka-Wei Lee. 2024. Math-llava: Bootstrapping mathematical reasoning for multimodal large language models. arXiv preprint arXiv:2406.17294.
  42. DongJae Shin, HyeonSeok Lim, Inho Won, ChangSu Choi, Minjun Kim, SeungWoo Song, HanGyeol Yoo, SangMin Kim, and KyungTae Lim. 2024. X-llava: Optimizing bilingual large vision-language alignment. In Findings of the Association for Computational Linguistics: NAACL 2024, page 2463–2473. Association for… find
  43. Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, and Marcus Rohrbach. 2019. Towards vqa models that can read. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8317–8326. find
  44. Mingjie Sun, Zhuang Liu, Anna Bair, and J. Zico Kolter. 2024. A simple and effective pruning approach for large language models. Preprint, arXiv:2306.11695. find
  45. Yu Tong, Weihai Lu, Xiaoxi Cui, Yifan Mao, and Zhejun Zhao. 2025. Dapt: Domain-aware prompt-tuning for multimodal fake news detection. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 7902–7911. find
  46. Yu Tong, Weihai Lu, Zhe Zhao, Song Lai, and Tong Shi. 2024. Mmdfnd: Multi-modal multi-domain fake news detection. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 1178– 1186. find
  47. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. Preprint…
  48. Jiaqi Wang, Hanqi Jiang, Yiheng Liu, Chong Ma, Xu Zhang, Yi Pan, Mengyuan Liu, Peiran Gu, Sichen Xia, Wenjun Li, Yutong Zhang, Zihao Wu, Zhengliang Liu, Tianyang Zhong, Bao Ge, Tuo Zhang, Ning Qiang, Xintao Hu, Xi Jiang, and 5 others. 2024a. A comprehensive review of multimodal large language models… — [arXiv:2408.01319](https://arxiv.org/abs/2408.01319) find
  49. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024b. Qwen2-vl: Enhancing vision-language model’s perception of the…
  50. Shida Wang, Chaohu Liu, Yubo Wang, and Linli Xu. 2025a. Fpedit: Robust llm fingerprinting through localized knowledge editing. Preprint, arXiv:2508.02092. find
  51. Xu Wang, Zihao Li, Benyou Wang, Yan Hu, and Difan Zou. 2025b. Model unlearning via sparse autoencoder subspace guided projections. Preprint, arXiv:2505.24428.
  52. Yubo Wang, Jianting Tang, Chaohu Liu, and Linli Xu. 2025c. Tracking the copyright of large vision-language models through parameter learning adversarial images. In The Thirteenth International Conference on Learning Representations. find
  53. Jiaxuan Wu, Wanli Peng, Hang Fu, Yiming Xue, and Juan Wen. 2025. Imf: Implicit fingerprint for large language models. Preprint, arXiv:2503.21805. — [arXiv:2503.21805](https://arxiv.org/abs/2503.21805) find
  54. Jiashu Xu, Fei Wang, Mingyu Derek Ma, Pang Wei Koh, Chaowei Xiao, and Muhao Chen. 2024a. Instructional fingerprinting of large language models. Preprint, arXiv:2401.12255. find
  55. Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. 2024b. A survey on knowledge distillation of large language models. Preprint, arXiv:2402.13116. — [arXiv:2402.13116](https://arxiv.org/abs/2402.13116) find
  56. Zhenhua Xu, Meng Han, and Wenpeng Xing. 2025a. Evertracer: Hunting stolen large language models via stealthy and robust probabilistic fingerprint. Preprint, arXiv:2509.03058. find
  57. Zhenhua Xu, Xubin Yue, Zhebo Wang, Qichen Liu, Xixiang Zhao, Jingxuan Zhang, Wenjun Zeng, Wengpeng Xing, Dezhang Kong, Changting Lin, and Meng Han. 2025b. Copyright protection for large language models: A survey of methods, challenges, and trends. Preprint, arXiv:2508.11548. — [arXiv:2508.11548](https://arxiv.org/abs/2508.11548) find
  58. Shojiro Yamabe, Futa Waseda, Tsubasa Takahashi, and Koki Wataoka. 2025. Mergeprint: Merge-resistant fingerprints for robust black-box ownership verification of large language models. Preprint, arXiv:2410.08604. find
  59. Enneng Yang, Li Shen, Guibing Guo, Xingwei Wang, Xiaochun Cao, Jie Zhang, and Dacheng Tao. 2025. Model merging in llms, mllms, and beyond: Methods, theories, applications and opportunities. Preprint, arXiv:2408.07666.
  60. Zhiguang Yang and Hanzhou Wu. 2024. A fingerprint for large language models. Preprint, arXiv:2407.01235. — [arXiv:2407.01235](https://arxiv.org/abs/2407.01235) find
  61. Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. 2023. A survey on multimodal large language models. CoRR, abs/2306.13549.
  62. Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490.
  63. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, and 1 others. 2023. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. arXiv preprint arXiv:2311.16502.
  64. Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, and Meng Han. 2025. Pree: Towards harmless and adaptive fingerprint editing in large language models via knowledge prefix enhancement. Preprint, arXiv:2509.00918. find
  65. Boyi Zeng, Lizheng Wang, Yuncong Hu, Yi Xu, Chenghu Zhou, Xinbing Wang, Yu Yu, and Zhouhan Lin. 2023. Huref: Human-readable fingerprint for large language models. Preprint, arXiv:2312.04828. — [arXiv:2312.04828](https://arxiv.org/abs/2312.04828) find
  66. Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024a. Mm-llms: Recent advances in multimodal large language models. Preprint, arXiv:2401.13601.
  67. Jialong Zhang, Zhongshu Gu, Jiyong Jang, Hui Wu, Marc Ph. Stoecklin, Heqing Huang, and Ian Molloy. 2018. Protecting intellectual property of deep neural networks with watermarking. In Proceedings of the 2018 on Asia Conference on Computer and Communications Security, ASIACCS ’18, page 159–172, New Y… find
  68. Jie Zhang, Dongrui Liu, Chen Qian, Linfeng Zhang, Yong Liu, Yu Qiao, and Jing Shao. 2024b. Reef: Representation encoding fingerprints for large language models. Preprint, arXiv:2410.14273. — [arXiv:2410.14273](https://arxiv.org/abs/2410.14273) find
  69. Xiaofan Zheng, Minnan Luo, and Xinghao Wang. 2025a. Unveiling fake news with adversarial arguments generated by multimodal large language models. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7862–7869, Abu Dhabi, UAE. Association for Computational Linguisti… find
  70. Xiaofan Zheng, Zinan Zeng, Heng Wang, Yuyang Bai, Yuhan Liu, and Minnan Luo. 2025b. From predictions to analyses: Rationale-augmented fake news detection with large vision-language models. In Proceedings of the ACM on Web Conference 2025, WWW ’25, page 5364–5375, New York, NY, USA. Association for C… find
  71. Xiaofan Zheng, Huixuan Zhang, and Xiaojun Wan. 2025c. Tracing training footprints: A calibration approach for membership inference attacks against multimodal large language models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 17179–17191, Suzhou, China. Association… find
  72. Zhiyuan Zhong, Zhen Sun, Yepang Liu, Xinlei He, and Guanhong Tao. 2025. Backdoor attack on vision language models with stealthy semantic manipulation. Preprint, arXiv:2506.07214. — [arXiv:2506.07214](https://arxiv.org/abs/2506.07214) find
  73. Xiaoling Zhou, Ou Wu, and Nan Yang. 2024a. Adversarial training with anti-adversaries. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):10210–10227. find
  74. Xiaoling Zhou, Ou Wu, Weiyao Zhu, and Ziyang Liang. 2022. Understanding difficulty-based sample weighting with a universal difficulty measure. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 68–84. Springer. find
  75. Xiaoling Zhou, Wei Ye, Zhemg Lee, Rui Xie, and Shikun Zhang. 2024b. Boosting model resilience via implicit adversarial data augmentation. arXiv preprint arXiv:2404.16307. — [arXiv:2404.16307](https://arxiv.org/abs/2404.16307) find
  76. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. CoRR, abs/2304.10592.
  77. Yuke Zhu, Oliver Groth, Michael Bernstein, and Li Fei-Fei. 2016. Visual7w: Grounded question answering in images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4995–5004.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zheng-2026-ghost-shell-synonym-aware-logit/