paper-with-me

홈 › Papers

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

2024-10-03 · Xiaogeng Liu, Peiran Li, Edward Suh, Yevgeniy Vorobeychik, Zhuoqing Mao, Somesh Jha, Patrick McDaniel, Huan Sun, Bo Li, Chaowei Xiao

In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human intervention or predefined scopes (e.g., specified candidate strategies), and use them for red-teaming. As a result, AutoDAN-Turbo can significantly outperform baseline methods, achieving a 74.3% higher average attack success rate on public benchmarks. Notably, AutoDAN-Turbo achieves an 88.5 attack success rate on GPT-4-1106-turbo. In addition, AutoDAN-Turbo is a unified framework that can incorporate existing human-designed jailbreak strategies in a plug-and-play manner. By integrating human-designed strategies, AutoDAN-Turbo can even achieve a higher attack success rate of 93.4 on GPT-4-1106-turbo.

📄 PDF Abstract BibTeX arXiv:2410.05295

Code (2)

safolab-wisc/autodan-turbo 공식 구현 pytorch
sheltonliu-n/autodan pytorch

Tasks

Red Teaming

Similar Papers 제목 키워드 기반

AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling

2025-10-06 · Xiaogeng Liu, Chaowei Xiao arxiv

Recent advancements in jailbreaking large language models (LLMs), such as AutoDAN-Turbo, have demonstrated the power of automated strategy discovery. AutoDAN-Turbo employs a lifelong learning agent to build a rich librar…

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs

2025-03-30 · Siqi Fan, Xiusheng Huang, Yiqun Yao, Xuezhi Fang 외

Large language models (LLMs) can carry out human-like dialogue, but unlike humans, they are stateless due to the superposition property. However, during multi-turn, multi-agent interactions, LLMs begin to exhibit consist…

Fact CheckingLifelong learning

LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners

2025-05-17 · Junhao Zheng, Xidi Cai, Qiuke Li, Duzhen Zhang 외

Lifelong learning is essential for intelligent agents operating in dynamic environments. Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time…

Language ModelingLanguage ModellingLarge Language ModelLifelong learning

TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction

2025-08-06 · Zewei Zhou, Seth Z. Zhao, Tianhui Cai, Zhiyu Huang 외 arxiv

End-to-end training of multi-agent systems offers significant advantages in improving multi-task performance. However, training such models remains challenging and requires extensive manual design and monitoring. In this…

Multi-Task Learning

CHIRPs: Change-Induced Regret Proxy metrics for Lifelong Reinforcement Learning

2024-09-05 · John Birkbeck, Adam Sobey, Federico Cerutti, Katherine Heseltine Hurley Flynn 외

Reinforcement learning (RL) agents are costly to train and fragile to environmental changes. They often perform poorly when there are many changing tasks, prohibiting their widespread deployment in the real world. Many L…

Lifelong learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)