LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

31 October 2023

Charlie Rogers-Smith

Papers citing "LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B"

15 / 65 papers shown

Title
Defending Against Unforeseen Failure Modes with Latent Adversarial Training Stephen Casper Lennart Schulze Oam Patel Dylan Hadfield-Menell AAML 57 28 0 08 Mar 2024
Guardrail Baselines for Unlearning in LLMs Pratiksha Thaker Yash Maurya Shengyuan Hu Zhiwei Steven Wu Virginia Smith MU 51 40 0 05 Mar 2024
Accelerating Greedy Coordinate Gradient via Probe Sampling Yiran Zhao Wenyue Zheng Tianle Cai Xuan Long Do Kenji Kawaguchi Anirudh Goyal Michael Shieh 51 11 0 02 Mar 2024
LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models Yichao Wu Yafei Xiang Shuning Huo Yulu Gong Penghao Liang 33 7 0 28 Feb 2024
Eight Methods to Evaluate Robust Unlearning in LLMs Aengus Lynch Phillip Guo Aidan Ewart Stephen Casper Dylan Hadfield-Menell ELM MU 42 57 0 26 Feb 2024
Immunization against harmful fine-tuning attacks Domenic Rosati Jan Wehner Kai Williams Lukasz Bartoszcze Jan Batzner Hassan Sajjad Frank Rudzicz AAML 65 16 0 26 Feb 2024
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment Jiong Wang Jiazhao Li Yiquan Li Xiangyu Qi Junjie Hu Yixuan Li P. McDaniel Muhao Chen Bo Li Chaowei Xiao AAML SILM 40 18 0 22 Feb 2024
Rethinking Machine Unlearning for Large Language Models Sijia Liu Yuanshun Yao Jinghan Jia Stephen Casper Nathalie Baracaldo ... Hang Li Kush R. Varshney Mohit Bansal Sanmi Koyejo Yang Liu AILaw MU 75 84 0 13 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-Bin Lin LLMAG LM&Ro 37 49 0 13 Feb 2024
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications Boyi Wei Kaixuan Huang Yangsibo Huang Tinghao Xie Xiangyu Qi Mengzhou Xia Prateek Mittal Mengdi Wang Peter Henderson AAML 60 79 0 07 Feb 2024
Vaccine: Perturbation-aware Alignment for Large Language Model Tiansheng Huang Sihao Hu Ling Liu 50 35 0 02 Feb 2024
Black-Box Access is Insufficient for Rigorous AI Audits Stephen Casper Carson Ezell Charlotte Siegmann Noam Kolt Taylor Lynn Curtis ... Michael Gerovitch David Bau Max Tegmark David M. Krueger Dylan Hadfield-Menell AAML 34 78 0 25 Jan 2024
Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying Adithya Renduchintala Tugrul Konuk Oleksii Kuchaiev MoMe 32 42 0 16 Nov 2023
Will releasing the weights of future large language models grant widespread access to pandemic agents? Anjali Gopal Nathan Helm-Burger Lenni Justen Emily H. Soice Tiffany Tzeng Geetha Jeyapragasan Simon Grimm Benjamin Mueller K. Esvelt 42 16 0 25 Oct 2023
Fine-Tuning Language Models from Human Preferences Daniel M. Ziegler Nisan Stiennon Jeff Wu Tom B. Brown Alec Radford Dario Amodei Paul Christiano G. Irving ALM 301 1,610 0 18 Sep 2019