@inproceedings{xing-etal-2026-silencing,
    title = "Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation",
    author = "Xing, Wenpeng  and
      Fang, Moran  and
      Wang, Guangtai  and
      Lin, Changting  and
      Han, Meng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.211/",
    pages = "4321--4334",
    ISBN = "979-8-89176-395-1",
    abstract = "While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, ranging from heuristic prompt engineering to computationally intensive optimization, often face significant trade-offs between effectiveness and efficiency. In this work, we propose Contextual Representation Ablation (CRA), a novel inference-time intervention framework designed to dynamically silence model guardrails. Predicated on the geometric insight that refusal behaviors are mediated by specific low-rank subspaces within the model{'}s hidden states, CRA identifies and suppresses these refusal-inducing activation patterns during decoding without requiring expensive parameter updates or training. Empirical evaluation across multiple safety-aligned open-source LLMs demonstrates that CRA significantly outperforms baselines. By revealing that safety constraints can be surgically ablated from internal representations, our findings expose the intrinsic fragility of current alignment mechanisms and underscore the urgent need for more robust latent-space defenses."
}