Qichen Liu

FORGETMARK: STEALTHY FINGERPRINT EMBEDDING VIA TARGETED UNLEARNING IN LANGUAGE MODELS

Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activations on benign inputs. We introduce \textsc{ForgetMark}, a stealthy fingerprinting framework that encodes provenance vi…