30
30
60
57
47
60
60
MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM Watermarks
MarkSec unifies evaluation of stealing, scrubbing, and spoofing attacks against LLM watermarks with quality-constrained success metrics under shared reporting protocols.
MarkSec is a framework unifying analysis of stealing, scrubbing, and spoofing attacks against LLM watermarks under shared detector calibration, metric definitions, and reporting protocols. It introduces a quality-constrained attack success metric that jointly assesses attack effectiveness and text quality. Experiments across representative watermark families, attacks, LLMs, and datasets show that attacks strongest by watermark removal alone can fall behind general rewriting when success requires acceptable text quality, and stealing-based scrubbers often underperform the best general-scrubbing baselines.
50
60
30
60
57
42
55
57
30
55
30
42
30
42
55
55
42
30
45
30
60
57
30
60
57
45
30
60
55
57
42
57
57