Gelei Deng (Nanyang Technological University), Yi Liu (Nanyang Technological University), Yuekang Li (University of New South Wales), Kailong Wang (Huazhong University of Science and Technology), Ying Zhang (Virginia Tech), Zefeng Li (Nanyang Technological University), Haoyu Wang (Huazhong University of Science and Technology), Tianwei Zhang (Nanyang Technological University), Yang Liu (Nanyang Technological University)

Large language models (LLMs), such as chatbots, have made significant strides in various fields but remain vulnerable to jailbreak attacks, which aim to elicit inappropriate responses. Despite efforts to identify these weaknesses, current strategies are ineffective against mainstream LLM chatbots, mainly due to undisclosed defensive measures by service providers. Our paper introduces MASTERKEY, a framework exploring the dynamics of jailbreak attacks and countermeasures. We present a novel method based on time-based characteristics to dissect LLM chatbot defenses. This technique, inspired by time-based SQL injection, uncovers the workings of these defenses and demonstrates a proof-of-concept attack on several LLM chatbots.

Additionally, MASTERKEY features an innovative approach for automatically generating jailbreak prompts that target well-defended LLM chatbots. By fine-tuning an LLM with jailbreak prompts, we create attacks with a 21.58% success rate, significantly higher than the 7.33% achieved by existing methods. We have informed service providers of these findings, highlighting the urgent need for stronger defenses. This work not only reveals vulnerabilities in LLMs but also underscores the importance of robust defenses against such attacks.

View More Papers

CrowdGuard: Federated Backdoor Detection in Federated Learning

Phillip Rieger (Technical University of Darmstadt), Torsten Krauß (University of Würzburg), Markus Miettinen (Technical University of Darmstadt), Alexandra Dmitrienko (University of Würzburg), Ahmad-Reza Sadeghi (Technical University of Darmstadt)

Read More

VETEOS: Statically Vetting EOSIO Contracts for the “Groundhog Day”...

Levi Taiji Li (University of Utah), Ningyu He (Peking University), Haoyu Wang (Huazhong University of Science and Technology), Mu Zhang (University of Utah)

Read More

Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech...

Xinfeng Li (Zhejiang University), Chen Yan (Zhejiang University), Xuancun Lu (Zhejiang University), Zihan Zeng (Zhejiang University), Xiaoyu Ji (Zhejiang University), Wenyuan Xu (Zhejiang University)

Read More

WIP: Delegation Related Privacy Issues in Matter

Ze Jin, Yiwei Fang, Haoqiang Wang (Chinese Academy of Sciences, University of Chinese Academy of Sciences, Indiana University Bloomington), Kexin Chen, Qixu Liu (Chinese Academy of Sciences, University of Chinese Academy of Sciences), Luyi Xing (Indiana University Bloomington)

Read More