@inproceedings{hu-etal-2026-jailbreak,
    title = "Jailbreak-Zero: A Path to {P}areto Optimal Red Teaming for Large Language Models",
    author = "Hu, Kai  and
      Aggarwal, Abhinav  and
      Khodabandeh, Mehran  and
      Zhang, David  and
      Hsin, Eric  and
      Chen, Li  and
      Jain, Ankit  and
      Fredrikson, Matt  and
      Bharadwaj, Akash",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2167/",
    pages = "46720--46746",
    ISBN = "979-8-89176-390-6",
    abstract = "This paper presents a novel Automated Red Teaming (ART) framework that shifts from example-based to policy-based evaluation, addressing critical limitations in scalability and validity. We define harmful content through abstract safety policies rather than specific static examples. We also introduce multiple evaluation objectives: risk coverage, semantic diversity, and fidelity, and discover Pareto trade-offs between them. We propose Jailbreak-Zero, a black-box method capable of both zero-shot generation and fine-tuned exploitation of a victim{'}s vulnerabilities to achieve Pareto optimality. Unlike prior approaches, it does not require expert-designed strategies/prompts, but still achieves superior, human-readable attacks against open-source and proprietary models (attack success rates of 99.5{\%} against GPT-4o and 96.0{\%} against Claude 3.5), even for unseen safety policies. It retains efficacy even after victim models undergo safety alignment, and exposes controls to navigate Pareto trade-offs \textit{without} retraining. Lastly, we show that Jailbreak-Zero is the best-performing ART method at a given compute budget. Code is available at: https://github.com/hukkai/jailbreak-zero/ ."
}