A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
Confguard: A simple and effective backdoor detection for large lan- guage models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 3roles
background 1polarities
background 1representative citing papers
QuantGuard is a pre-quantization method using differentiable rounding controls, error-guided reversal constraints, output consistency, and weight regularization on a small calibration set to suppress quantization-conditioned backdoors while preserving performance.
BackFlush detects backdoors via susceptibility amplification and eliminates them with RoPE unlearning to reach 1% ASR and 99% clean accuracy while preserving watermarks.
citing papers explorer
-
Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors
QuantGuard is a pre-quantization method using differentiable rounding controls, error-guided reversal constraints, output consistency, and weight regularization on a small calibration set to suppress quantization-conditioned backdoors while preserving performance.
-
BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models
BackFlush detects backdoors via susceptibility amplification and eliminates them with RoPE unlearning to reach 1% ASR and 99% clean accuracy while preserving watermarks.