Paper recorded by Signals 4 on 2026-09-10 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11
Category: cs.CL · 自然语言处理 · first seen 2026-09-11
Large language models are often fine-tuned, shared, or downloaded from third parties, so a deployed model may carry a hidden backdoor that behaves normally on benign inputs but switches to attacker-controlled behavior when a secret trigger appears. While backdoors can be audited before deployment, runtime monitoring remains important for models that are frequently updated. The challenge is that LL