Title
CacheTrap: Injecting Trojans in LLMs without Leaving any Traces in Inputs or Weights Mohaiminul Al Nahian Abeer Matar A. Almalky Gamana Aragonda Ranyang Zhou Sabbir Ahmed Dmitry Ponomarev Li Yang Shaahin Angizi Adnan Siraj Rakin 40 0 0 27 Nov 2025
Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning James R. M. Black Moritz S. Hanke Aaron Maiwald Tina Hernandez-Boussard Oliver M. Crook Jaspreet Pannu 65 0 0 24 Nov 2025
Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education Xin Yi Yue Li Dongsheng Shi Linlin Wang Xiaoling Wang Liang He AAML 211 0 0 18 Nov 2025
REMIND: Input Loss Landscapes Reveal Residual Memorization in Post-Unlearning LLMs Liran Cohen Yaniv Nemcovesky Avi Mendelson MU AAML CLL KELM 279 0 0 06 Nov 2025
Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler Zixuan Hu Li Shen Zhenyi Wang Yongxian Wei Dacheng Tao AAML 147 0 0 31 Oct 2025
A Survey on Unlearning in Large Language Models Ruichen Qiu Jiajun Tan Jiayue Pu Honglin Wang Xiao-Shan Gao Fei Sun MU AILaw PILM 606 0 0 29 Oct 2025
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training Zheng-Xin Yong Stephen H. Bach LRM 224 0 0 23 Oct 2025
A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space Bingjie Zhang Yibo Yang Renzhe Dandan Guo Jindong Gu Philip Torr Bernard Ghanem 255 0 0 16 Oct 2025
Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning Guozhi Liu Qi Mu Tiansheng Huang Xinhua Wang Li Shen Weiwei Lin Zhang Li 116 1 0 11 Oct 2025
LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics Chongyu Fan Changsheng Wang Yancheng Huang Soumyadeep Pal Sijia Liu MU ELM 176 0 0 08 Oct 2025
Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach X. Li Y. Wang Bo Li AAML 209 0 0 01 Oct 2025
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning Yicheng Lang Yihua Zhang Chongyu Fan Changsheng Wang Jinghan Jia Sijia Liu MU 345 0 0 01 Oct 2025
Understanding the Dilemma of Unlearning for Large Language Models Qingjie Zhang Haoting Qian Zhicong Huang Cheng Hong Shiyu Huang Ke Xu Chao Zhang Han Qiu MU 232 1 0 29 Sep 2025
Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction Yuanbo Xie Yingjie Zhang Tianyun Liu Duohe Ma Tingwen Liu AAML 115 1 0 18 Sep 2025
Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning Filip Sondej Yushi Yang MU 346 0 0 15 Sep 2025
Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning Weitao Feng Lixu Wang Tianyi Wei Jie Zhang Chongyang Gao Sinong Zhan Peizhuo Lv Wei Dong AAML OffRL CLL 72 0 0 28 Aug 2025
Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks Jack Youstra Mohammed Mahfoud Yang Yan Henry Sleight Ethan Perez Mrinank Sharma AAML 144 2 0 23 Aug 2025
Gradient Surgery for Safe LLM Fine-Tuning Biao Yi Jiahao Li Baolei Zhang Lihai Nie Tong Li Tiansheng Huang Zheli Liu 102 1 0 10 Aug 2025
Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks Bing Han Feifei Zhao Dongcheng Zhao Guobin Shen Ping Wu Yu Shi Yi Zeng 176 0 0 08 Aug 2025
LLM Unlearning Without an Expert Curated Dataset Xiaoyuan Zhu Muru Zhang Ollie Liu Robin Jia Willie Neiswanger MU 247 0 0 08 Aug 2025
Estimating Worst-Case Frontier Risks of Open-Weight LLMs Eric Wallace Olivia Watkins Miles Wang Kai Chen Chris Koch 154 7 0 05 Aug 2025
SDD: Self-Degraded Defense against Malicious Fine-tuningAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 ZiXuan Chen Weikai Lu Xin Lin Ziqian Zeng AAML 139 0 0 27 Jul 2025
A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction Xiaohua Feng Jiaming Zhang Fengyuan Yu C. Wang Li Zhang Kaixiang Li Yuyuan Li Chaochao Chen Jianwei Yin MU 246 2 0 26 Jul 2025
Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility Brendan Murphy Dillon Bowen Shahrad Mohammadzadeh Tom Tseng Julius Broomfield Adam Gleave Kellin Pelrine 258 2 0 15 Jul 2025
Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language ModelsInternational Conference on Learning Representations (ICLR), 2025 Biao Yi Tiansheng Huang Sishuo Chen Tong Li Zheli Liu Zhixuan Chu Yiming Li AAML 227 18 0 19 Jun 2025
FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Christina Q. Knight Kaustubh Deshpande Ved Sirdeshmukh Meher Mankikar Scale Red Team SEAL Research Team Julian Michael AAML ELM 291 2 0 17 Jun 2025
Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization Filip Sondej Yushi Yang Mikołaj Kniejski Marcel Windys MU 341 2 0 14 Jun 2025
Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Yeonwoo Jang Shariqah Hossain Ashwin Sreevatsa Diogo Cruz AAML MU 216 2 0 11 Jun 2025
AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin Shuo Yang Qihui Zhang Yuyang Liu Yue Huang Xiaojun Jia ... Jiayu Yao Jigang Wang Hailiang Dai Yibing Song Li Yuan 202 8 0 10 Jun 2025
Distillation Robustifies Unlearning Bruce W. Lee Addie Foote Alex Infanger Leni Shor Harish Kamath Jacob Goldman-Wetzler Bryce Woodworth Alex Cloud Alexander Matt Turner MU 381 4 0 06 Jun 2025
Benchmarking Misuse Mitigation Against Covert Adversaries Davis Brown Mahdi Sabbaghi Luze Sun Avi Schwarzschild George Pappas Eric Wong Hamed Hassani 132 2 0 06 Jun 2025
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning Changsheng Wang Yihua Zhang Jinghan Jia Parikshit Ram Dennis L. Wei Yuguang Yao Soumyadeep Pal Nathalie Baracaldo Sijia Liu MU 250 4 0 02 Jun 2025
Existing Large Language Model Unlearning Evaluations Are Inconclusive Zhili Feng Yixuan Even Xu Avi Schwarzschild Robert Kirk Xander Davies Yarin Gal Avi Schwarzschild J. Zico Kolter MU ELM 149 5 0 31 May 2025
Shape it Up! Restoring LLM Safety during Finetuning ShengYun Peng Pin-Yu Chen Jianfeng Chi Seongmin Lee Duen Horng Chau LLMAG 284 3 0 22 May 2025
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning Biao Yi Tiansheng Huang Baolei Zhang Tong Li Lihai Nie Zheli Liu Li Shen MU AAML 287 5 0 22 May 2025
Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning Thibaud Gloaguen Mark Vero Robin Staab Martin Vechev AAML 425 0 0 22 May 2025
Mitigating Fine-tuning Risks in LLMs via Safety-Aware Probing Optimization Chengcan Wu Zhixin Zhang Zeming Wei Yihao Zhang Meng Sun AAML 216 8 0 22 May 2025
Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study Kaustubh Ponkshe Shaan Shah Raghav Singhal Praneeth Vepakomma 334 0 0 20 May 2025
Security practices in AI developmentAi & Society (AS), 2025 Petr Spelda Vit Stritecky 206 1 0 17 May 2025
Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness Hanyu Duan Yi Yang Ahmed Abbasi Kar Yan Tam MU OnRL 245 1 0 16 May 2025
Layered Unlearning for Adversarial Relearning Timothy Qian Vinith Suriyakumar Ashia Wilson Dylan Hadfield-Menell MU 310 1 0 14 May 2025
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety Zihan Guan Mengxuan Hu Ronghang Zhu Sheng Li Anil Vullikanti AAML 303 10 0 11 May 2025
Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization Wenjun Cao AAML 215 2 0 07 May 2025
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging Aladin Djuhera S. Kadhe Praneet Adusumilli Syed Zawad Holger Boche MoMe 237 14 0 21 Mar 2025
Improving LLM Safety Alignment with Dual-Objective Optimization Xuandong Zhao Will Cai Tianneng Shi David Huang Licong Lin Song Mei Kurt Thomas AAML MU 453 14 0 05 Mar 2025
Beyond Release: Access Considerations for Generative AI Systems Irene Solaiman Rishi Bommasani Dan Hendrycks Ariel Herbert-Voss Yacine Jernite Aviya Skowron Andrew Trask 504 3 0 23 Feb 2025
A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens Sophie Xhonneux David Dobre Mehrnaz Mohfakhami Leo Schwinn Gauthier Gidel 545 2 0 22 Feb 2025
Adversarial ML Problems Are Getting Harder to Solve and to Evaluate Javier Rando Jie Zhang Nicholas Carlini F. Tramèr AAML ELM 336 18 0 04 Feb 2025
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities Zora Che Stephen Casper Robert Kirk Anirudh Satheesh Stewart Slocum ... Zikui Cai Bilal Chughtai Y. Gal Furong Huang Dylan Hadfield-Menell MU AAML ELM 567 23 0 03 Feb 2025
Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation Yun Wang Tiansheng Huang Li Shen Huanjin Yao Haotian Luo Rui Liu Naiqiang Tan Jiaxing Huang Dacheng Tao AAML MoMe CLL 387 10 0 30 Jan 2025