Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models
On the map: LLM safety and security → Jailbreaking
Abstract (arXiv)
We present a novel black-box jailbreaking framework that integrates multiple LLM-as-Attacker strategies to deliver highly transferable and effective attacks. The framework is grounded in three key insights from prior jailbreaking research and practice: ensemble approaches outperform single methods in exposing aligned LLM vulnerabilities, malicious instructions vary in jailbreaking difficulty requiring tailored optimization, and disrupting semantic coherence of malicious prompts can manipulate their embeddings to boost success rates. Validated in the Competition for LLM and Agent Safety 2024, our solution achieved top rankings in the Jailbreaking Attack Track.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 9 of its 11 references that are in the map. First posted on arXiv 31 Oct 2024.
Builds on
9 of 11 references.
Closest ancestors · 8
Same direction, newest first
- 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey5 Jul
- 2024Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis16 Jun
- 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan
- 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
- 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models3 Oct
- 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
- 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
- 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
Other references · 1
- 2024On Prompt-Driven Safeguarding for Large Language Modelscited by 109
Built on by
Not cited yet.