Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment techniques have been developed to improve the public usability and safety of LLMs. Yet, the potential for generating harmful content through these models seems to persist. This paper explores the concept of jailbreaking LLMs-reversing their alignment through adversarial triggers. Previous methods, such as soft embedding prompts, manually crafted prompts, and gradient-based automatic prompts, have had limited success on black-box models due to their requirements for model access and for producing a low variety of manually crafted prompts, making them susceptible to being blocked. This paper introduces a novel approach using reinforcement learning to optimize adversarial triggers, requiring only inference API access to the target model and a small surrogate model. Our method, which leverages a BERTScore-based reward function, enhances the transferability and effectiveness of adversarial triggers on new black-box models. We demonstrate that this approach improves the performance of adversarial triggers on a previously untested language model.
MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors
Xin Tong School of Information and Cyber Security People’s Public Security University of China(信息与网络安全学院 中国人民公安大学);Zhi Lin School of Safety Science Tsinghua University(安全科学学院 清华大学);Jingya Wang School of Information and Cyber Security People’s Public Security University of China(信息与网络安全学院 中国人民公安大学);Meng Han Intelligent Fusion Research Center Zhejiang University(智能融合研究中心 浙江大学);Bo Jin* The Third Research Institute of the Ministry of Public Security of China(中华人民共和国公安部第三研究所)
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
National University of Singapore(新加坡国立大学);Fudan University(复旦大学);Tsinghua University(清华大学);Zhejiang University(浙江大学);University of Science and Technology of China(中国科学技术大学);vivo
Bridge-Coder: Unlocking LLMs' Potential to Overcome Language Gaps in Low-Resource Code
The Hong Kong University of Science and Technology(香港科技大学);Southern University of Science and Technology(南方科技大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
BrainLLM: Generative Language Decoding from Brain Recordings
Tsinghua University, Beijing, China(清华大学);University of Amsterdam, Amsterdam, Netherlands(阿姆斯特丹大学);University of Copenhagen, Copenhagen, Denmark(哥本哈根大学);Lappeenranta-Lahti University of Technology, Lappeenranta, Finland(拉普兰塔-拉赫蒂技术大学)
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters
Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Hong Kong University of Science and Technology(香港科技大学);Tencent AI Lab(腾讯人工智能实验室)
Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Beijing Institute of AI Safety and Governance(北京人工智能安全与治理研究院);Beijing Key Laboratory of Safe AI and Superalignment(北京安全人工智能与超对齐重点实验室);BrainCog Lab, Institute of Automation, Chinese Academy of Sciences(脑认知实验室,中国科学院自动化研究所)
Byte-token Enhanced Language Models for Temporal Point Processes Analysis
Independent Researcher(独立研究者);Southeast University(东南大学);Center for Applied Statistics and School of Statistics, Renmin University of China(应用统计中心和中国人民大学统计学院)