Fetching the paper…
Reading the bibliography…
Despite advancements in enhancing LLM safety against jailbreak attacks, evaluating LLM defenses remains a challenge, with current methods often lacking explainability and generalization to complex scenarios, leading to incomplete assessments (e.g., direct judgment without reasoning, low F1 score of GPT-4 in complex cases, bias in multilingual scenarios).
Upper and lower probabilities induced by a multivalued mapping
Arthur P Dempster · 2008
Earlier work this paper cites.
Deng entropy
Yong Deng · 2016
Earlier work this paper cites.
Towards deep learning models resistant to adversarial attacks
Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu · 2018
Earlier work this paper cites.
Lora: Low-rank adaptation of large language models
Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen · 2021
Earlier work this paper cites.
Detecting language model attacks with perplexity
Gabriel Alon and Michael Kamfonas · 2023
Earlier work this paper cites.
Red-teaming large language models using chain of utterances for safety-alignment
Rishabh Bhardwaj and Soujanya Poria · 2023
Earlier work this paper cites.
Federico Bianchi, Mirac Suzgun, Giuseppe Attanasio, Paul Röttger, Dan Jurafsky, Tatsunori Hashimoto, and James Zou · 2023
Earlier work this paper cites.
Defending against alignment-breaking attacks via robustly aligned llm
Bochuan Cao, Yuanpu Cao, Lu Lin, and Jinghui Chen · 2023
Earlier work this paper cites.
Jailbreaking black box large language models in twenty queries, 2023
Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J. Pappas, and Eric Wong · 2023
Earlier work this paper cites.
Analyzing the inherent response tendency of llms: Real-world instructions-driven jailbreak
Yanrui Du, Sendong Zhao, Ming Ma, Yuhan Chen, and Bing Qin · 2023
Earlier work this paper cites.
Llm censorship: A machine learning challenge or a computer security problem?
David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, and Vardan Papyan · 2023
Earlier work this paper cites.
Catastrophic jailbreak of open-source llms via exploiting generation
Yangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li, and Danqi Chen · 2023
Earlier work this paper cites.
Llama guard: Llm-based input-output safeguard for human-ai conversations
Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, et al · 2023
Earlier work this paper cites.
Rain: Your language models can align themselves without finetuning
Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, and Hongyang Zhang · 2023
Earlier work this paper cites.
Tree of attacks: Jailbreaking black-box llms automatically
Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum Anderson, Yaron Singer, and Amin Karbasi · 2023
Earlier work this paper cites.
Fine-tuning aligned language models compromises safety, even when users do not intend to!
Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson · 2023
Earlier work this paper cites.
Understanding hidden context in preference learning: Consequences for rlhf
Anand Siththaranjan, Cassidy Laidlaw, and Dylan Hadfield-Menell · 2023
Cited alongside, same era.
Llama 2: Open foundation and fine-tuned chat models
Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al · 2023
Cited alongside, same era.
Do-not-answer: A dataset for evaluating safeguards in llms
Yuxia Wang, Haonan Li, Xudong Han, Preslav Nakov, and Timothy Baldwin · 2023
Cited alongside, same era.
Jailbroken: How does llm safety training fail?
Alexander Wei, Nika Haghtalab, and Jacob Steinhardt · 2023
Cited alongside, same era.
Defending chatgpt against jailbreak attack via self-reminders
Yueqi Xie, Jingwei Yi, Jiawei Shao, Justin Curl, Lingjuan Lyu, Qifeng Chen, Xing Xie, and Fangzhao Wu · 2023
Cited alongside, same era.
Prp: Propagating universal perturbations to attack large language model guard-rails
Neal Mangaokar, Ashish Hooda, Jihye Choi, Shreyas Chandrashekaran, Kassem Fawaz, Somesh Jha, and Atul Prakash · 2024
Closest in time.
Advprompter: Fast adaptive adversarial prompting for llms
Anselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos, and Yuandong Tian · 2024
Closest in time.
Gpt-4 jailbreaks itself with near-perfect success using self-explanation, 2024
Govind Ramesh, Yao Dou, and Wei Xu · 2024
Closest in time.
Jailbreakeval: An integrated toolkit for evaluating jailbreak attempts against large language models
Delong Ran, Jinyuan Liu, Yichen Gong, Jingyi Zheng, Xinlei He, Tianshuo Cong, and Anyu Wang · 2024
Closest in time.
Great, now write an article about that: The crescendo multi-turn llm jailbreak attack
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
GPTFUZZER: red teaming large language models with auto-generated jailbreak prompts
Jiahao Yu, Xingwei Lin, Zheng Yu, and Xinyu Xing · 2023
Cited alongside, same era.
Large language model unlearning
Yao Yuanshun, Xu Xiaojun, and Liu Yang · 2023
Cited alongside, same era.
Universal and transferable adversarial attacks on aligned language models
Andy Zou, Zifan Wang, J. Zico Kolter, and Matt Fredrikson · 2023
Cited alongside, same era.
Jailbreaking leading safety-aligned llms with simple adaptive attacks
Maksym Andriushchenko, Francesco Croce, and Nicolas Flammarion · 2024
Cited alongside, same era.
Take a look at it! rethinking how to evaluate language model jailbreak
Hongyu Cai, Arjun Arunasalam, Leo Y Lin, Antonio Bianchi, and Z Berkay Celik · 2024
Cited alongside, same era.
Jailbreakbench: An open robustness benchmark for jailbreaking large language models
Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J Pappas, Florian Tramer, et al · 2024
Cited alongside, same era.
Attacking large language models with projected gradient descent
Simon Geisler, Tom Wollschläger, MHI Abdalla, Johannes Gasteiger, and Stephan Günnemann · 2024
Cited alongside, same era.
Mark Russinovich, Ahmed Salem, and Ronen Eldan · 2024
Closest in time.
Prompt stealing attacks against large language models
Zeyang Sha and Yang Zhang · 2024
Closest in time.
“Do Anything Now”: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, and Yang Zhang · 2024
Closest in time.
A strongreject for empty jailbreaks, 2024
Alexandra Souly, Qingyuan Lu, Dillon Bowen, Tu Trinh, Elvis Hsieh, Sana Pandey, Pieter Abbeel, Justin Svegliato, Scott Emmons, Olivia Watkins, and Sam Toyer · 2024
Closest in time.
Sandwich attack: Multi-language mixture adaptive attack on llms, 2024
Bibek Upadhayay and Vahid Behzadan · 2024
Closest in time.
Mitigating fine-tuning jailbreak attack with backdoor enhanced alignment
Jiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Muhao Chen, Junjie Hu, Yixuan Li, Bo Li, and Chaowei Xiao · 2024
Closest in time.
A new era in llm security: Exploring security concerns in real-world llm-based systems
Fangzhou Wu, Ning Zhang, Somesh Jha, Patrick McDaniel, and Chaowei Xiao · 2024
Closest in time.
Bag of tricks: Benchmarking of jailbreak attacks on llms
Zhao Xu, Fan Liu, and Hao Liu · 2024
Closest in time.
Chain of attack: a semantic-driven contextual multi-turn attacker for llm, 2024
Xikang Yang, Xuehai Tang, Songlin Hu, and Jizhong Han · 2024
Closest in time.
Rigorllm: Resilient guardrails for large language models against undesired content
Zhuowen Yuan, Zidi Xiong, Yi Zeng, Ning Yu, Ruoxi Jia, Dawn Song, and Bo Li · 2024
Closest in time.
Robust prompt optimization for defending language models against jailbreaking attacks
Andy Zhou, Bo Li, and Haohan Wang · 2024
Closest in time.
Improving alignment and robustness with circuit breakers, 2024
Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, Rowan Wang, Zico Kolter, Matt Fredrikson, and Dan Hendrycks · 2024
Closest in time.