Paper ID: 2410.23558

Transferable Ensemble Black-box Jailbreak Attacks on Large Language Models

Yiqi Yang, Hongye Fu

In this report, we propose a novel black-box jailbreak attacking framework that incorporates various LLM-as-Attacker methods to deliver transferable and powerful jailbreak attacks. Our method is designed based on three key observations from existing jailbreaking studies and practices. First, we consider an ensemble approach should be more effective in exposing the vulnerabilities of an aligned LLM compared to individual attacks. Second, different malicious instructions inherently vary in their jailbreaking difficulty, necessitating differentiated treatment to ensure more efficient attacks. Finally, the semantic coherence of a malicious instruction is crucial for triggering the defenses of an aligned LLM; therefore, it must be carefully disrupted to manipulate its embedding representation, thereby increasing the jailbreak success rate. We validated our approach by participating in the Competition for LLM and Agent Safety 2024, where our team achieved top performance in the Jailbreaking Attack Track.

Submitted: Oct 31, 2024