With the widespread application of Large Language Models across various domains, their security issues have increasingly garnered significant attention from both academic and industrial communities. This study conducts sampling and normalization of the parameters of the LLM to generate visual representations and heatmaps of parameter distributions, revealing notable discrepancies in parameter distributions among certain layers within the hidden layers. Further analysis involves calculating statistical metrics for each layer, followed by the computation of a Comprehensive Sensitivity Score based on these metrics, which identifies the lower layers as being particularly sensitive to the generation of harmful content. Based on this finding, we employ a Freeze training strategy, selectively performing Supervised Fine-Tuning only on the lower layers. Experimental results demonstrate that this method significantly reduces training duration and GPU memory consumption while maintaining a high jailbreak success rate and a high harm score, outperforming the results achieved by applying the LoRA method for SFT across all layers. Additionally, the method has been successfully extended to other open-source large models, validating its generality and effectiveness across different model architectures. Furthermore, we compare our method with ohter jailbreak method, demonstrating the superior performance of our approach. By innovatively proposing a method to statistically analyze and compare large model parameters layer by layer, this study provides new insights into the interpretability of large models. These discoveries emphasize the necessity of continuous research and the implementation of adaptive security measures in the rapidly evolving field of LLMs to prevent potential jailbreak attack risks, thereby promoting the development of more robust and secure LLMs.
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);People’s Public Security University of China(中国人民公安大学);Tsinghua University(清华大学)
Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);RealAI;Tsinghua University(清华大学)
Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
Stony Brook University(石溪大学);Binghamton University(宾汉姆顿大学);University of Iowa(爱荷华大学);Dartmouth College(达特茅斯学院);Georgia Institute of Technology(佐治亚理工学院)
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全国家重点实验室);State Key Laboratory of Internet Architecture, Tsinghua University(清华大学互联网架构国家重点实验室);Huazhong University of Science and Technology(华中科技大学);Shanghai AI Laboratory(上海人工智能实验室);East China Normal University(华东师范大学)
ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models
iFLYTEK Security Laboratory(iFLYTEK安全实验室);Anhui SparkShield Intelligent Technology Co., Ltd.(安徽SparkShield智能科技有限公司);Peking University(北京大学);School of Automation, University of Electronic Science and Technology of China(电子科技大学自动化学院);Northwest University(西北大学);University of New South Wales(新南威尔士大学);National Computer Network Emergency Response Technical Team/Coordination Center of China(中国国家计算机网络应急技术处置协调中心)
Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);People’s Public Security University of China(中国人民公安大学)
Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
School of Cyberspace Science and Technology, Beijing Institute of Technology(信息科学与技术学院,北京理工大学);School of Computer Science and Technology, Beijing Institute of Technology(计算机科学与技术学院,北京理工大学);School of Computer Science, University of Auckland(计算机科学学院,奥克兰大学);QAX Security Center, Qi-AnXin Technology Group Inc.(QAX安全中心,启安新科技集团);Qi-AnXin Technology Group Inc.(启安新科技集团);Zhongguancun Laboratory(中关村实验室)
PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips
Oregon State University(俄勒冈州立大学);University of British Columbia(不列颠哥伦比亚大学);University of Toronto(多伦多大学);George Mason University(乔治·梅森大学);Rutgers University(罗格斯大学);University of Texas at Arlington(德克萨斯大学阿灵顿分校)
Geneshift: Impact of different scenario shift on Jailbreaking LLM
National University of Singapore(新加坡国立大学);NUS Graduate School(新加坡国立大学研究生院);Integrative Sciences and Engineering Programme(整合科学与工程项目);Institute of Data Science (IDS)(数据科学研究院);School of Computing(计算机学院)
PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
School of Cyber Science and Engineering, Sichuan University(四川大学网络空间安全学院);School of Cyber Security, Tianjin University(天津大学网络安全学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
Multi-step Jailbreaking Privacy Attacks on ChatGPT
Hong Kong University of Science and Technology(香港科技大学);Peking University(北京大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Notre Dame(圣母大学)