@inproceedings{schwarz-etal-2025-graph,
    title = "Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt. Generation for Enhanced {LLM} Content Moderation",
    author = "Schwarz, Daniel  and
      Bespalov, Dmitriy  and
      Wang, Zhe  and
      Kulkarni, Ninad  and
      Qi, Yanjun",
    editor = "Calabrese, Agostina  and
      de Kock, Christine  and
      Nozza, Debora  and
      Plaza-del-Arco, Flor Miriam  and
      Talat, Zeerak  and
      Vargas, Francielle",
    booktitle = "Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.woah-1.44/",
    pages = "482--489",
    ISBN = "979-8-89176-105-6",
    abstract = "As large language models (LLMs) become increasingly prevalent, ensuring their robustness against adversarial misuse is crucial. This paper introduces the GAP (Graph of Attacks with Pruning) framework, an advanced approach for generating stealthy jailbreak prompts to evaluate and enhance LLM safeguards. GAP addresses limitations in existing tree-based methods by implementing an interconnected graph structure that enables knowledge sharing across attack paths. Our experimental evaluation demonstrates GAP{'}s superiority over existing techniques, achieving a 20.8{\%} increase in attack success rates while reducing query costs by 62.7{\%}. GAP consistently outperforms state-of-the-art methods across various open and closed LLMs, with attack success rates of 96{\%}. Additionally, we present specialized variants like GAP-Auto for automated seed generation and GAP-VLM for multimodal attacks. GAP-generated prompts prove highly effective in improving content moderation systems, increasing true positive detection rates by 108.5{\%} and accuracy by 183.6{\%} when used for fine-tuning."
}