🧑‍🔬 Who cites Maksym Andriushchenko

366 citations of their works from 303 papers of our library (of the 149,439 whose bibliographies we read) · 80 with a page here, the most cited first · ← Maksym Andriushchenko

1. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextarXiv:2403.05530Gemini Team, Petko Georgiev, Ving Ian Lei, et al.2024 · 1,589 citations
2. OpenAI o1 System CardarXiv:2412.16720OpenAI, Aaron Jaech, Adam Kalai, et al.2024 · 1,110 citations
3. Jailbreaking Black Box Large Language Models in Twenty QueriesarXiv:2310.08419Patrick Chao, Alexander Robey, Edgar Dobriban, et al.2023 · 553 citations
4. JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language ModelsConference on Neural Information Processing Systems (NeurIPS)Patrick Chao, Edoardo Debenedetti, Alexander Robey, et al.2024 · 277 citations
5. Tree of Attacks: Jailbreaking Black-Box LLMs AutomaticallyConference on Neural Information Processing Systems (NeurIPS)Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, et al.2023 · 251 citations
6. Refusal in Language Models Is Mediated by a Single DirectionarXiv:2406.11717Andy Arditi, Oscar Obeso, Aaquib Syed, et al.2024 · 196 citations
7. AI Alignment: A Comprehensive SurveyarXiv:2310.19852Jiaming Ji, Tianyi Qiu, Boyuan Chen, et al.2023 · 173 citations
8. SmoothLLM: Defending Large Language Models Against Jailbreaking AttacksarXiv:2310.03684Alexander Robey, Eric Wong, Hamed Hassani, et al.2023 · 164 citations
9. A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and TrustworthinessACM Transactions on Intelligent Systems and TechnologyFali Wang, Zhiwei Zhang, Xianren Zhang, et al.2024 · 159 citations
10. DeepInception: Hypnotize Large Language Model to Be JailbreakerarXiv:2311.03191Xuan Li, Zhanke Zhou, Jianing Zhu, et al.2023 · 141 citations
11. Jailbreak and Guard Aligned Language Models with Only Few In-Context DemonstrationsarXiv:2310.06387Zeming Wei, Yifei Wang, Ang Li, et al.2023 · 130 citations
12. Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive AttacksarXiv:2404.02151Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion2024 · 118 citations
13. Deliberative Alignment: Reasoning Enables Safer Language ModelsarXiv:2412.16339Melody Y. Guan, Manas Joglekar, Eric Wallace, et al.2024 · 115 citations
14. A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and RecommendationsConference on Empirical Methods in Natural Language Processing (EMNLP)Md Tahmid Rahman Laskar, Sawsan Alqahtani, M Saiful Bari, et al.2024 · 105 citations
15. Jailbreak Attacks and Defenses Against Large Language Models: A SurveyarXiv:2407.04295Sibo Yi, Yule Liu, Zhen Sun, et al.2024 · 97 citations
16. Safety Alignment Should Be Made More Than Just a Few Tokens DeeparXiv:2406.05946Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, et al.2024 · 97 citations
17. WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language ModelsConference on Neural Information Processing Systems (NeurIPS)Liwei Jiang, Kavel Rao, Seungju Han, et al.2024 · 92 citations
18. SORRY-Bench: Systematically Evaluating Large Language Model Safety RefusalarXiv:2406.14598Tinghao Xie, Xiangyu Qi, Yi Zeng, et al.2024 · 87 citations
19. Improving Alignment and Robustness with Circuit BreakersConference on Neural Information Processing Systems (NeurIPS)Andy Zou, Long Phan, Justin Wang, et al.2024 · 83 citations
20. A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and BeyondarXiv:2503.21614Xiaoye Qu, Yafu Li, Zhao-Chen Su, et al.2025 · 55 citations
21. Introducing v0.5 of the AI Safety Benchmark from MLCommonsarXiv:2404.12241Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed, et al.2024 · 38 citations
22. VLSBench: Unveiling Visual Leakage in Multimodal SafetyAnnual Meeting of the Association for Computational Linguistics (ACL)Xuhao Hu, Dongrui Liu, Hao Li, et al.2025 · 32 citations
23. The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1International Joint Conference on Natural Language Processing (IJCNLP)Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao, et al.2025 · 30 citations
24. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingarXiv:2501.18837Mrinank Sharma, Meg Tong, Jesse Mu, et al.2025 · 29 citations
25. Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from JailbreakingConference on Empirical Methods in Natural Language Processing (EMNLP)Junda Zhu, Lingyong Yan, Shuaiqiang Wang, et al.2025 · 21 citations
26. Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal TrainingAnnual Meeting of the Association for Computational Linguistics (ACL)Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, et al.2025 · 19 citations
27. LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution ShiftsAnnual Meeting of the Association for Computational Linguistics (ACL)Qibing Ren, Hao Li, Dongrui Liu, et al.2025 · 18 citations
28. Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Sarah Ball, Frauke Kreuter, Nina Panickssery2026 · 17 citations
29. When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex CiphersarXiv:2402.10601Divij Handa, Zehua Zhang, Amir Saeidi, et al.2024 · 15 citations
30. Safety Alignment via Constrained Knowledge UnlearningAnnual Meeting of the Association for Computational Linguistics (ACL)Zesheng Shi, Yucheng Zhou, Jing Li, et al.2025 · 13 citations
31. AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak DefenderConference on Empirical Methods in Natural Language Processing (EMNLP)Weixiang Zhao, Jiahe Guo, Yulin Hu, et al.2025 · 11 citations
32. Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety AlignmentConference on Empirical Methods in Natural Language Processing (EMNLP)Hao Li, Lijun Li, Zhenghao Lu, et al.2025 · 11 citations
33. Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable RewardAnnual Meeting of the Association for Computational Linguistics (ACL)Weiyang Guo, Zesheng Shi, Zeen Zhu, et al.2026 · 10 citations
34. SafeKey: Amplifying Aha-Moment Insights for Safety ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP)Kaiwen Zhou, Xuandong Zhao, Jayanth Srinivasa, et al.2025 · 9 citations
35. Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical ExpressionFindings of the Association for Computational LinguisticsJingyu Peng, Maolin Wang, Nan Wang, et al.2026 · 8 citations
36. False Sense of Security: Why Probing-based Malicious Input Detection Fails to GeneralizeFindings of the Association for Computational LinguisticsCheng Wang, Zeming Wei, Qin Liu, et al.2026 · 5 citations
37. FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Masoomali Fatehkia, Enes Altinisik, Husrev Taha Sencar2026 · 5 citations
38. HiddenGuard: Fine-Grained Safe Generation with Specialized Representation RouterAnnual Meeting of the Association for Computational Linguistics (ACL)Lingrui Mei, Shenghua Liu, Yiwei Wang, et al.2026 · 4 citations
39. Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Zirui Song, Qian Jiang, Mingxuan Cui, et al.2026 · 3 citations
40. CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-TuningAnnual Meeting of the Association for Computational Linguistics (ACL)Biao Yi, Tiansheng Huang, Baolei Zhang, et al.2026 · 3 citations
41. IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian LanguagesConference of the European Chapter of the Association for Computational Linguistics (EACL)Priyaranjan Pattnayak, Sanchari Chowdhuri2026 · 3 citations
42. Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?Findings of the Association for Computational LinguisticsYuan Xin, Dingfan Chen, Linyi Yang, et al.2026 · 3 citations
43. TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process RewardsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiqiao Xiong, Ouxiang Li, Zhuo Liu, et al.2026 · 3 citations
44. Universal Jailbreak Suffixes Are Strong Attention HijackersTransactions of the Association for Computational Linguistics (TACL)Matan Ben-Tov, Mor Geva, Mahmood Sharif2026 · 3 citations
45. Unraveling LLM Jailbreaks Through Safety Knowledge NeuronsConference of the European Chapter of the Association for Computational Linguistics (EACL)Chongwen Zhao, Yutong Ke, Kaizhu Huang2026 · 3 citations
46. In-Context Representation HijackingAnnual Meeting of the Association for Computational Linguistics (ACL)Itay Yona, Amir Sarid, Michael Karasik, et al.2026 · 2 citations
47. KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language ModelsSIGUL Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered LanguagesWajdi Zaghouani, Shimaa Amer Ibrahim, Aruzhan Muratbek, et al.2026 · 2 citations
48. PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health EthicsFindings of the Association for Computational LinguisticsYaling Shen, Stephanie Fong, Yiwen Jiang, et al.2026 · 2 citations
49. Activation-Guided Local Editing for Jailbreaking AttacksAnnual Meeting of the Association for Computational Linguistics (ACL)Jiecong Wang, Haoran Li, Hao Peng, et al.2026 · 1 citation
50. Adversarial Decoding: Generating Readable Documents for Adversarial ObjectivesFindings of the Association for Computational LinguisticsCollin Zhang, Tingwei Zhang, Vitaly Shmatikov2026 · 1 citation
51. Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience ReplayFindings of the Association for Computational LinguisticsHao Wang, Yanting Wang, Hao Li, et al.2026 · 1 citation
52. Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Rui Pu, Chaozhuo Li, Rui Ha, et al.2026 · 1 citation
53. From Attack Surfaces to Actual Operations: A Survey of Modern LLM JailbreaksFindings of the Association for Computational LinguisticsRuikang Zhou, Changsheng Sun, Mark Huasong Meng2026 · 1 citation
54. Reasoning Up the Instruction Ladder for Controllable Language ModelsFindings of the Association for Computational LinguisticsZishuo Zheng, Vidhisha Balachandran, Chan Young Park, et al.2026 · 1 citation
55. SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation SteeringAnnual Meeting of the Association for Computational Linguistics (ACL)Utsav Maskey, Sumit Yadav, Mark Dras, et al.2026 · 1 citation
56. When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning ModelsFindings of the Association for Computational LinguisticsYingzhi Mao, Chunkang Zhang, Junxiang Wang, et al.2026 · 1 citation
57. HAMSA: Hijacking Aligned Compact Models via Stealthy AutomationarXiv:2508.16484Alexey Krylov, Iskander Vagizov, Dmitrii Korzh, et al.2025 · 1 citation
58. Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Wentao Zhang, Yan Zhuang, ZhuHang Zheng, et al.2026
59. Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety AlignmentWorkshop on Trustworthy NLPZhiyu Xue, Zimo Qi, Guangliang Liu, et al.2026
60. Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language ModelsFindings of the Association for Computational LinguisticsBoyang Zhang, Istemi Ekin Akkus, Ruichuan Chen, et al.2026
61. Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation MonitoringAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaohao Luo, Ying Wei, Rui Zhao2026
62. Inverting the Shield: Systematically Generating Safety Tests from Policy SpecificationsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoyue Lu, Xianglin Yang, Haijun Liu, et al.2026
63. Mind the Language Gap: Assessing LLM Safety in ItalianLanguage Resources and Evaluation Conference (LREC)Elena Marafatto, Roberto Navigli2026
64. MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language ModelsWorkshop on Multilinguality in the Era of Large Language ModelsRishabh Makwana, Mamta Mamta, Deeksha Varshney, et al.2026
65. Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Ye Yu, Haibo Jin, Yaoning Yu, et al.2026
66. Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language ModelsFindings of the Association for Computational LinguisticsRagib Amin Nihal, Rui Wen, Kazuhiro Nakadai, et al.2026
67. Policy Compliance of User Requests in Natural Language for AI SystemsAnnual Meeting of the Association for Computational Linguistics (ACL)Pedro Cisneros-Velarde2026
68. Preventing Safety Drift in Large Language Models via Coupled Weight and Activation ConstraintsFindings of the Association for Computational LinguisticsSongping Peng, Zhiheng Zhang, Daojian Zeng, et al.2026
69. Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Wai Man Si, Mingjie Li, Michael Backes, et al.2026
70. Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival AnalysisWorkshop on Trustworthy NLPZvi Topol2026
71. RAMP: Risk-Aware Multi-Turn Planning for Jailbreak Red-TeamingFindings of the Association for Computational LinguisticsYize Liu, Yunyun Hou, Aina Sui2026
72. SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast AsiaFindings of the Association for Computational LinguisticsPanuthep Tasawong, Jian Gang Ngui, Alham Fikri Aji, et al.2026
73. SEA-SafeguardBench: Culturally Grounded Safety Benchmark for Southeast Asian LanguagesFindings of the Association for Computational LinguisticsPanuthep Tasawong, Jian Gang Ngui, Alham Fikri Aji, et al.2026
74. SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance TriggerAnnual Meeting of the Association for Computational Linguistics (ACL)Sunguk Shin, Fangzhao Wu, Byung-Jun Lee, et al.2026
75. Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation AblationFindings of the Association for Computational LinguisticsWenpeng Xing, Moran Fang, Guangtai Wang, et al.2026
76. StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Huawei Zheng, Xinqi Jiang, Sen Yang, et al.2026
77. The Geometry of Refusal: Linear Instability in Safety-Aligned LLMsWorkshop on Trustworthy NLPShivam Ratnakar, Kartikeya Vats2026
78. Thinking Twice Makes Large Language Models Safer and More HelpfulFindings of the Association for Computational LinguisticsYutao Mou, Yuxiao Luo, Shikun Zhang, et al.2026
79. TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety AlignmentAnnual Meeting of the Association for Computational Linguistics (ACL)Zhewen Tan, Wenhan Yu, Jianfeng Si, et al.2026
80. When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Zafir Shamsi, Nikhil Chekuru, Zachary Guzman, et al.2026

223 more citing papers of our library have no page here yet.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/maksym-andriushchenko/cited-by/