Defusing the Trigger: Tail-Risk-Informed Attention Rebalancing for LLM Backdoor Mitigation

Backdoored large language models (LLMs) exhibit attacker-specified behavior at inference time while retaining normal performance on benign inputs. Existing mitigations often require parameter updates and trusted clean data, or rely on auxiliary generation and repeated model execution, complicating deployment. Across diverse backdoor mechanisms, successful activations exhibit stronger tail concentration in attention over semantic-content tokens than benign inputs and unsuccessful trigger activations. This pattern provides a sample-internal control signal to selectively regulate suspicious attention dynamics. We propose TIARA, a tail-risk-informed attention rebalancing approach for inferenc...

<iframe src="https://silytics.si/embed/item/dddc58fe-5b5f-4d55-b8b9-040110e8d1d3" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.