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!"

45 / 395 papers shown

Title
Weak-to-Strong Jailbreaking on Large Language Models Xuandong Zhao Xianjun Yang Tianyu Pang Chao Du Lei Li Yu-Xiang Wang William Yang Wang 21 49 0 30 Jan 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 13 75 0 25 Jan 2024
InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance Pengyu Wang Dong Zhang Linyang Li Chenkun Tan Xinghao Wang Ke Ren Botian Jiang Xipeng Qiu LLMSV 13 39 0 20 Jan 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 21 58 0 18 Jan 2024
AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models Dong Shu Mingyu Jin Suiyuan Zhu Beichen Wang Zihao Zhou Chong Zhang Yongfeng Zhang ELM 37 12 0 17 Jan 2024
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs Yi Zeng Hongpeng Lin Jingwen Zhang Diyi Yang Ruoxi Jia Weiyan Shi 15 179 0 12 Jan 2024
Examining Forgetting in Continual Pre-training of Aligned Large Language Models Chen An Li Hung-Yi Lee CLL KELM 18 8 0 06 Jan 2024
Large Language Models for Social Networks: Applications, Challenges, and Solutions Jingying Zeng Richard Huang Waleed Malik Langxuan Yin Bojan Babic Danny Shacham Xiao Yan Jaewon Yang Qi He 14 3 0 04 Jan 2024
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity Andrew Lee Xiaoyan Bai Itamar Pres Martin Wattenberg Jonathan K. Kummerfeld Rada Mihalcea 61 95 0 03 Jan 2024
Alleviating Hallucinations of Large Language Models through Induced Hallucinations Yue Zhang Leyang Cui Wei Bi Shuming Shi HILM 34 49 0 25 Dec 2023
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models Alan Chan Ben Bucknall Herbie Bradley David M. Krueger 8 6 0 22 Dec 2023
MetaAID 2.5: A Secure Framework for Developing Metaverse Applications via Large Language Models Hongyin Zhu 23 6 0 22 Dec 2023
Exploiting Novel GPT-4 APIs Kellin Pelrine Mohammad Taufeeque Michal Zajkac Euan McLean Adam Gleave SILM 10 20 0 21 Dec 2023
Learning and Forgetting Unsafe Examples in Large Language Models Jiachen Zhao Zhun Deng David Madras James Zou Mengye Ren MU KELM CLL 76 15 0 20 Dec 2023
Bypassing the Safety Training of Open-Source LLMs with Priming Attacks Jason Vega Isha Chaudhary Changming Xu Gagandeep Singh AAML 14 18 0 19 Dec 2023
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack Yu Fu Yufei Li Wen Xiao Cong Liu Yue Dong AAML 29 5 0 12 Dec 2023
Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs Zhuo Zhang Guangyu Shen Guanhong Tao Shuyang Cheng Xiangyu Zhang 23 13 0 08 Dec 2023
LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem Yingqiang Ge Yujie Ren Wenyue Hua Shuyuan Xu Juntao Tan Yongfeng Zhang LLMAG 12 27 0 06 Dec 2023
The Philosopher's Stone: Trojaning Plugins of Large Language Models Tian Dong Minhui Xue Guoxing Chen Rayne Holland Shaofeng Li Yan Meng Zhen Liu Haojin Zhu AAML 13 9 0 01 Dec 2023
Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework Matthew Pisano Peter Ly Abraham Sanders Bingsheng Yao Dakuo Wang T. Strzalkowski Mei Si AAML 14 23 0 16 Nov 2023
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections Yuanpu Cao Bochuan Cao Jinghui Chen 15 23 0 15 Nov 2023
SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models Bertie Vidgen Nino Scherrer Hannah Rose Kirk Rebecca Qian Anand Kannappan Scott A. Hale Paul Röttger ALM ELM 19 26 0 14 Nov 2023
Removing RLHF Protections in GPT-4 via Fine-Tuning Qiusi Zhan Richard Fang R. Bindu Akul Gupta Tatsunori Hashimoto Daniel Kang MU AAML 13 90 0 09 Nov 2023
Making Harmful Behaviors Unlearnable for Large Language Models Xin Zhou Yi Lu Ruotian Ma Tao Gui Qi Zhang Xuanjing Huang MU 22 7 0 02 Nov 2023
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game Sam Toyer Olivia Watkins Ethan Mendes Justin Svegliato Luke Bailey ... Karim Elmaaroufi Pieter Abbeel Trevor Darrell Alan Ritter Stuart J. Russell 6 71 0 02 Nov 2023
BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B Pranav M. Gade Simon Lermen Charlie Rogers-Smith Jeffrey Ladish ALM AI4MH 9 23 0 31 Oct 2023
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B Simon Lermen Charlie Rogers-Smith Jeffrey Ladish ALM 15 80 0 31 Oct 2023
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks Xiaoyi Chen Siyuan Tang Rui Zhu Shijun Yan Lei Jin Zihao Wang Liya Su Zhikun Zhang XiaoFeng Wang Haixu Tang AAML PILM 11 16 0 24 Oct 2023
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation Yangsibo Huang Samyak Gupta Mengzhou Xia Kai Li Danqi Chen AAML 17 264 0 10 Oct 2023
Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations Zeming Wei Yifei Wang Ang Li Yichuan Mo Yisen Wang 40 233 0 10 Oct 2023
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks Alexander Robey Eric Wong Hamed Hassani George J. Pappas AAML 38 215 0 05 Oct 2023
All Languages Matter: On the Multilingual Safety of Large Language Models Wenxuan Wang Zhaopeng Tu Chang Chen Youliang Yuan Jen-tse Huang Wenxiang Jiao Michael R. Lyu ALM LRM 31 31 0 02 Oct 2023
Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review Pengzhou Cheng Zongru Wu Wei Du Haodong Zhao Wei Lu Gongshen Liu SILM AAML 18 15 0 12 Sep 2023
$Decolonial AI Alignment: Openness, Viśe\d{s}a-Dharma, and Including Excluded Knowledges$ Decolonial AI Alignment: Openness, Viśe\d{s}a-Dharma, and Including Excluded Knowledges Kush R. Varshney 15 2 0 10 Sep 2023
Image Hijacks: Adversarial Images can Control Generative Models at Runtime Luke Bailey Euan Ong Stuart J. Russell Scott Emmons VLM MLLM 11 78 0 01 Sep 2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback Stephen Casper Xander Davies Claudia Shi T. Gilbert Jérémy Scheurer ... Erdem Biyik Anca Dragan David M. Krueger Dorsa Sadigh Dylan Hadfield-Menell ALM OffRL 28 436 0 27 Jul 2023
AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks Alexander Tornede Difan Deng Theresa Eimer Joseph Giovanelli Aditya Mohan ... Sarah Segel Daphne Theodorakopoulos Tanja Tornede Henning Wachsmuth Marius Lindauer 20 22 0 13 Jun 2023
ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs Zihao Zhao Sheng Wang Jinchen Gu Yitao Zhu Lanzhuju Mei Zixu Zhuang Zhiming Cui Qian Wang Dinggang Shen LM&MA 18 34 0 25 May 2023
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned Deep Ganguli Liane Lovitt John Kernion Amanda Askell Yuntao Bai ... Nicholas Joseph Sam McCandlish C. Olah Jared Kaplan Jack Clark 218 441 0 23 Aug 2022
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning Zhenting Wang Juan Zhai Shiqing Ma AAML 114 97 0 26 May 2022
Training language models to follow instructions with human feedback Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright ... Amanda Askell Peter Welinder Paul Christiano Jan Leike Ryan J. Lowe OSLM ALM 301 11,730 0 04 Mar 2022
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 315 8,261 0 28 Jan 2022
Towards Continual Knowledge Learning of Language Models Joel Jang Seonghyeon Ye Sohee Yang Joongbo Shin Janghoon Han Gyeonghun Kim Stanley Jungkyu Choi Minjoon Seo CLL KELM 222 150 0 07 Oct 2021
Entity-Based Knowledge Conflicts in Question Answering Shayne Longpre Kartik Perisetla Anthony Chen Nikhil Ramesh Chris DuBois Sameer Singh HILM 235 236 0 10 Sep 2021
The Power of Scale for Parameter-Efficient Prompt Tuning Brian Lester Rami Al-Rfou Noah Constant VPVLM 278 3,784 0 18 Apr 2021