[Sentient Launches AI Model Fingerprinting Benchmark 'Fingerprinting Leaderboard' to Test AI Models' Provenance Verification] Odaily Planet Daily News: Sentient Foundation has announced the launch of an open benchmarking platform, Fingerprinting Leaderboard, along with an open-source toolkit, mlprints, designed to evaluate AI model fingerprinting technologies and their robustness against adversarial attacks. Previously, research published by Sentient Labs at SaTML 2026 revealed that ten existing model fingerprinting techniques, including its Perinucleus method, could all be bypassed when faced with sophisticated adaptive attacks. This benchmark aims to validate the embedding effectiveness and removal resistance of model fingerprints through open testing, helping developers retain proof of ownership while sharing model weights. In the future, the benchmark aims to deeply integrate model fingerprints with the model's own capabilities, such that any attempt to remove the fingerprint would simultaneously impair the model's functionality.