@inproceedings{wang-etal-2026-activation,
    title = "Activation-Guided Local Editing for Jailbreaking Attacks",
    author = "Wang, Jiecong  and
      Li, Haoran  and
      Peng, Hao  and
      Zeng, Ziqian  and
      Wang, Zihao  and
      Du, Haohua  and
      Yu, Zhengtao",
    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.801/",
    pages = "17614--17633",
    ISBN = "979-8-89176-390-6",
    abstract = "As Large Language Models (LLMs) become indispensable assistants, they remain vulnerable to misuse. Jailbreaking is an essential adversarial technique for red-teaming models to uncover and patch security flaws. However, existing jailbreak methods suffer from significant limitations. Token-level jailbreak attacks often produce incoherent or unreadable inputs and exhibit poor transferability, while prompt-level attacks lack scalability and rely heavily on manual effort and human ingenuity. We propose AGILE, a concise and effective two-stage framework that combines the advantages of these approaches. The first stage performs a one-shot, scenario-based generation of context and rephrases the original malicious query to obscure its harmful intent. The second stage utilizes information from the model{'}s hidden states to guide fine-grained edits, effectively steering the model{'}s internal representation of the input from a malicious one toward a benign one. Extensive experiments demonstrate that AGILE achieves state-of-the-art Attack Success Rate, with gains of up to 37.74{\%} over the strongest baseline, and AGILE exhibits excellent transferability to black-box and large-scale models. Our code is available at https://github.com/SELGroup/AGILE."
}