Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

5 October 2023

Yi Zeng

Papers citing "Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!"

50 / 395 papers shown

Title
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey Tiansheng Huang Sihao Hu Fatih Ilhan Selim Furkan Tekin Ling Liu AAML 38 21 0 26 Sep 2024
A Survey on Offensive AI Within Cybersecurity Sahil Girhepuje Aviral Verma Gaurav Raina AAML 15 2 0 26 Sep 2024
MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks Giandomenico Cornacchia Giulio Zizzo Kieran Fraser Muhammad Zaid Hameed Ambrish Rawat Mark Purcell 16 1 0 26 Sep 2024
Elephant in the Room: Unveiling the Impact of Reward Model Quality in Alignment Yan Liu Xiaoyuan Yi Xiaokang Chen Jing Yao Jingwei Yi Daoguang Zan Zheng Liu Xing Xie Tsung-Yi Ho ALM 26 0 0 26 Sep 2024
An Adversarial Perspective on Machine Unlearning for AI Safety Jakub Łucki Boyi Wei Yangsibo Huang Peter Henderson F. Tramèr Javier Rando MU AAML 66 31 0 26 Sep 2024
LLM Echo Chamber: personalized and automated disinformation Tony Ma 16 0 0 24 Sep 2024
Backtracking Improves Generation Safety Yiming Zhang Jianfeng Chi Hailey Nguyen Kartikeya Upasani Daniel M. Bikel Jason Weston Eric Michael Smith SILM 34 5 0 22 Sep 2024
PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach Zhihao Lin Wei Ma Mingyi Zhou Yanjie Zhao Haoyu Wang Yang Liu Jun Wang Li Li AAML 30 5 0 21 Sep 2024
Towards LifeSpan Cognitive Systems Yu Wang Chi Han Tongtong Wu Xiaoxin He Wangchunshu Zhou ... Zexue He Wei Wang Gholamreza Haffari Heng Ji Julian McAuley KELM CLL 83 1 0 20 Sep 2024
Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning Essa Jan Nouar Aldahoul Moiz Ali Faizan Ahmad Fareed Zaffar Yasir Zaki 18 3 0 18 Sep 2024
Prompt Obfuscation for Large Language Models David Pape Thorsten Eisenhofer Thorsten Eisenhofer Lea Schönherr AAML 31 2 0 17 Sep 2024
Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective Van-Cuong Pham Thien Huu Nguyen LLMSV 33 3 0 16 Sep 2024
ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs Hua Shen Tiffany Knearem Reshmi Ghosh Yu-Ju Yang Tanushree Mitra Yun Huang Yun Huang 35 0 0 15 Sep 2024
Improving governance outcomes through AI documentation: Bridging theory and practice Amy A. Winecoff Miranda Bogen 16 2 0 13 Sep 2024
Alignment of Diffusion Models: Fundamentals, Challenges, and Future Buhua Liu Shitong Shao Bao Li Lichen Bai Zhiqiang Xu Haoyi Xiong James Kwok Sumi Helal Zeke Xie 37 11 0 11 Sep 2024
DiPT: Enhancing LLM reasoning through diversified perspective-taking H. Just Mahavir Dabas Lifu Huang Ming Jin Ruoxi Jia LRM 32 1 0 10 Sep 2024
Exploring Straightforward Conversational Red-Teaming George Kour Naama Zwerdling Marcel Zalmanovici Ateret Anaby-Tavor Ora Nova Fandina E. Farchi AAML 42 1 0 07 Sep 2024
Recent Advances in Attack and Defense Approaches of Large Language Models Jing Cui Yishi Xu Zhewei Huang Shuchang Zhou Jianbin Jiao Junge Zhang PILM AAML 47 1 0 05 Sep 2024
The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs Bocheng Chen Hanqing Guo Guangjing Wang Yuanda Wang Qiben Yan AAML 37 4 0 01 Sep 2024
Acceptable Use Policies for Foundation Models Kevin Klyman 23 14 0 29 Aug 2024
FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench Aman Priyanshu Supriti Vijay AAML 23 1 0 28 Aug 2024
Legilimens: Practical and Unified Content Moderation for Large Language Model Services Jialin Wu Jiangyi Deng Shengyuan Pang Yanjiao Chen Jiayang Xu Xinfeng Li Wenyuan Xu 32 6 0 28 Aug 2024
Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models Wenxuan Zhang Philip H. S. Torr Mohamed Elhoseiny Adel Bibi 43 9 0 27 Aug 2024
Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation Haoyu Wang Bingzhe Wu Yatao Bian Yongzhe Chang Xueqian Wang Peilin Zhao 51 2 0 20 Aug 2024
Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Tiansheng Huang Gautam Bhattacharya Pratik Joshi Josh Kimball Ling Liu AAML MoMe 47 16 0 18 Aug 2024
How Susceptible are LLMs to Influence in Prompts? Sotiris Anagnostidis Jannis Bulian LRM 25 16 0 17 Aug 2024
MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector Wenjie Fu Huandong Wang Chen Gao Guanghua Liu Yong Li Tao Jiang 21 3 0 16 Aug 2024
Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks Jiawei Zhao Kejiang Chen Xiaojian Yuan Weiming Zhang AAML 23 2 0 15 Aug 2024
Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles Xiongtao Sun Deyue Zhang Dongdong Yang Quanchen Zou Hui Li AAML 19 11 0 08 Aug 2024
WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models Prannaya Gupta Le Qi Yau Hao Han Low I-Shiang Lee Hugo Maximus Lim ... Jia Hng Koh Dar Win Liew Rishabh Bhardwaj Rajat Bhardwaj Soujanya Poria ELM LM&MA 44 4 0 07 Aug 2024
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs Jingtong Su Mingyu Lee SangKeun Lee 30 7 0 02 Aug 2024
Tamper-Resistant Safeguards for Open-Weight LLMs Rishub Tamirisa Bhrugu Bharathi Long Phan Andy Zhou Alice Gatti ... Andy Zou Dawn Song Bo Li Dan Hendrycks Mantas Mazeika AAML MU 42 36 0 01 Aug 2024
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? Richard Ren Steven Basart Adam Khoja Alice Gatti Long Phan ... Alexander Pan Gabriel Mukobi Ryan H. Kim Stephen Fitz Dan Hendrycks ELM 26 19 0 31 Jul 2024
Machine Unlearning in Generative AI: A Survey Zheyuan Liu Guangyao Dou Zhaoxuan Tan Yijun Tian Meng-Long Jiang MU 29 13 0 30 Jul 2024
Can Editing LLMs Inject Harm? Canyu Chen Baixiang Huang Zekun Li Zhaorun Chen Shiyang Lai ... Xifeng Yan William Wang Philip H. S. Torr Dawn Song Kai Shu KELM 38 11 0 29 Jul 2024
The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models Zihui Wu Haichang Gao Jianping He Ping Wang 17 6 0 25 Jul 2024
Know Your Limits: A Survey of Abstention in Large Language Models Bingbing Wen Jihan Yao Shangbin Feng Chenjun Xu Yulia Tsvetkov Bill Howe Lucy Lu Wang 49 5 0 25 Jul 2024
Can Large Language Models Automatically Jailbreak GPT-4V? Yuanwei Wu Yue Huang Yixin Liu Xiang Li Pan Zhou Lichao Sun SILM 30 1 0 23 Jul 2024
RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent Huiyu Xu Wenhui Zhang Zhibo Wang Feng Xiao Rui Zheng Yunhe Feng Zhongjie Ba Kui Ren AAML LLMAG 26 11 0 23 Jul 2024
AI Act for the Working Programmer Holger Hermanns Anne Lauber-Rönsberg Philip Meinel Sarah Sterz Hanwei Zhang 25 1 0 23 Jul 2024
LLMmap: Fingerprinting For Large Language Models Dario Pasquini Evgenios M. Kornaropoulos G. Ateniese 50 6 0 22 Jul 2024
Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context Nilanjana Das Edward Raff Manas Gaur AAML 29 2 0 19 Jul 2024
The Better Angels of Machine Personality: How Personality Relates to LLM Safety Jie M. Zhang Dongrui Liu Chao Qian Ziyue Gan Yong-jin Liu Yu Qiao Jing Shao LLMAG PILM 40 12 0 17 Jul 2024
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training Youliang Yuan Wenxiang Jiao Wenxuan Wang Jen-tse Huang Jiahao Xu Tian Liang Pinjia He Zhaopeng Tu 30 19 0 12 Jul 2024
Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture Jiayang Song Yuheng Huang Zhehua Zhou Lei Ma 37 6 0 10 Jul 2024
Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey) K. Kenthapadi M. Sameki Ankur Taly HILM ELM AILaw 34 12 0 10 Jul 2024
ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context Victoria R. Li Yida Chen Naomi Saphra 27 3 0 09 Jul 2024
Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders Jinseok Kim Jaewon Jung Sangyeop Kim S. Park Sungzoon Cho 42 0 0 09 Jul 2024
Jailbreak Attacks and Defenses Against Large Language Models: A Survey Sibo Yi Yule Liu Zhen Sun Tianshuo Cong Xinlei He Jiaxing Song Ke Xu Qi Li AAML 34 77 0 05 Jul 2024
Securing Multi-turn Conversational Language Models Against Distributed Backdoor Triggers Terry Tong Jiashu Xu Qin Liu Muhao Chen AAML SILM 30 1 0 04 Jul 2024