Study tests black-box watermarks for hyperdimensional classifiers
AdaptHD and OnlineHD kept verification at 1% trigger exposure with at most 0.58 points of mean accuracy loss.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #model-watermarking
From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models
SimPrint embeds recoverable semantic fingerprints in open-weight LLMs, enabling black-box ownership verification that survives fine-tuning, pruning, quantization and merging.