BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

31 October 2023

Papers citing "BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B"

23 / 23 papers shown

Title
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety Zihan Guan Mengxuan Hu Ronghang Zhu Sheng Li Anil Vullikanti AAML 36 0 0 11 May 2025
AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations Dillon Bowen Ann-Kathrin Dombrowski Adam Gleave Chris Cundy ELM 55 0 0 17 Mar 2025
DarkBench: Benchmarking Dark Patterns in Large Language Models Esben Kran Hieu Minh "Jord" Nguyen Akash Kundu Sami Jawhar Jinsuk Park Mateusz Maria Jurewicz 59 1 0 13 Mar 2025
The Pitfalls of "Security by Obscurity" And What They Mean for Transparent AI Peter Hall Olivia Mundahl Sunoo Park 86 0 0 30 Jan 2025
Toxicity of the Commons: Curating Open-Source Pre-Training Data Catherine Arnett Eliot Jones Ivan P. Yamshchikov Pierre-Carl Langlais 41 2 0 29 Oct 2024
SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis Aidan Wong He Cao Zijing Liu Yu-Feng Li 55 2 0 21 Oct 2024
Locking Down the Finetuned LLMs Safety Minjun Zhu Linyi Yang Yifan Wei Ningyu Zhang Yue Zhang 59 10 0 14 Oct 2024
Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates Xiaosen Zheng Tianyu Pang Chao Du Qian Liu Jing Jiang Min Lin 53 8 0 09 Oct 2024
Applying Refusal-Vector Ablation to Llama 3.1 70B Agents Simon Lermen Mateusz Dziemian Govind Pimpale LLMAG 33 4 0 08 Oct 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 62 1 0 05 Sep 2024
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models Yi Zeng Weiyu Sun Tran Ngoc Huynh Dawn Song Bo Li Ruoxi Jia AAML LLMSV 42 19 0 24 Jun 2024
Safety Alignment Should Be Made More Than Just a Few Tokens Deep Xiangyu Qi Ashwinee Panda Kaifeng Lyu Xiao Ma Subhrajit Roy Ahmad Beirami Prateek Mittal Peter Henderson 47 83 0 10 Jun 2024
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses Xiaosen Zheng Tianyu Pang Chao Du Qian Liu Jing Jiang Min Lin AAML 68 32 0 03 Jun 2024
Societal Adaptation to Advanced AI Jamie Bernardi Gabriel Mukobi Hilary Greaves Lennart Heim Markus Anderljung 51 5 0 16 May 2024
The Necessity of AI Audit Standards Boards David Manheim Sammy Martin Mark Bailey Mikhail Samin Ross Greutzmacher 38 7 0 11 Apr 2024
Immunization against harmful fine-tuning attacks Domenic Rosati Jan Wehner Kai Williams Lukasz Bartoszcze Jan Batzner Hassan Sajjad Frank Rudzicz AAML 65 17 0 26 Feb 2024
A Chinese Dataset for Evaluating the Safeguards in Large Language Models Yuxia Wang Zenan Zhai Haonan Li Xudong Han Lizhi Lin Zhenxuan Zhang Jingru Zhao Preslav Nakov Timothy Baldwin 47 9 0 19 Feb 2024
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey Zhichen Dong Zhanhui Zhou Chao Yang Jing Shao Yu Qiao ELM 58 59 0 14 Feb 2024
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast Xiangming Gu Xiaosen Zheng Tianyu Pang Chao Du Qian Liu Ye Wang Jing Jiang Min Lin LLMAG LM&Ro 37 50 0 13 Feb 2024
R-Judge: Benchmarking Safety Risk Awareness for LLM Agents Tongxin Yuan Zhiwei He Lingzhong Dong Yiming Wang Ruijie Zhao ... Binglin Zhou Fangqi Li Zhuosheng Zhang Rui Wang Gongshen Liu ELM 41 63 0 18 Jan 2024
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models Alan Chan Ben Bucknall Herbie Bradley David M. Krueger 19 6 0 22 Dec 2023
Sparks of Artificial General Intelligence: Early experiments with GPT-4 Sébastien Bubeck Varun Chandrasekaran Ronen Eldan J. Gehrke Eric Horvitz ... Scott M. Lundberg Harsha Nori Hamid Palangi Marco Tulio Ribeiro Yi Zhang ELM AI4MH AI4CE ALM 435 3,045 0 22 Mar 2023
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Jason W. Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter F. Xia Ed H. Chi Quoc Le Denny Zhou LM&Ro LRM AI4CE ReLM 450 8,727 0 28 Jan 2022