Robust watermarks leak detectable patterns into neural network feature channels, enabling single-image, no-box watermark removal and forgery.
URL https://openai.com/sora
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
Robust watermarks leak detectable patterns into neural network feature channels, enabling single-image, no-box watermark removal and forgery.