RLCracker is a reinforcement learning attack that erases LLM watermarks at 98.5% success rate with minimal data and generalizes across ten schemes and multiple model sizes.
arXiv preprint arXiv:2402.14007 (2024)
3 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
3
Pith papers citing it
3
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Signature filtering learns unreliable tokens with MILP and removes them at detection time, raising true positive rates from 8-31% to 78-99% across Kgw, Sweet, Unigram, and Exp watermarks on multiple corpora and LLMs while controlling false positives.
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
citing papers explorer
-
RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
RLCracker is a reinforcement learning attack that erases LLM watermarks at 98.5% success rate with minimal data and generalizes across ten schemes and multiple model sizes.
-
Signature filtering: a lightweight enhancement for statistical watermark detection in large language models
Signature filtering learns unreliable tokens with MILP and removes them at detection time, raising true positive rates from 8-31% to 78-99% across Kgw, Sweet, Unigram, and Exp watermarks on multiple corpora and LLMs while controlling false positives.
-
Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.