LLM Agent Backdoor Decontamination
Arxiv
pdf
2026-08-01T00:00:00
arXiv Paper — PDF not available.
Only the Executive Summary is available here. To read or download the full paper, visit the
arXiv abstract page.
Abstract
Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defenders do not know the existing trigger, they cannot unlearn it directly. One decontamination strategy is to install a known backdoor (defensive poisoning) then to unlearn it, hoping that the original unknown backdoor is removed as a side effect. However, this procedure has uncertain outcomes: the original backdoor may persist or be erased or rerouted, among other possibilities.
Loading executive summary...