Watermarking for Byzantine Robust LLM Training

본문 미리보기

arXiv:2610.14289v1 Announce Type: new Abstract: LLM watermarking has emerged as a promising approach for detecting downstream model misuse in centralized settings, but extending it to federated learning (FL) presents unique challenges. In particular, FL systems often rely on strong robust aggregators to defend against poisoning attacks. We empirically show that a malicious server can exploit these same aggregators as effective watermark-removal mechanisms during training, causing representative