Transfer-based no-box watermark evasion largely fails without aligned surrogate models, and a simple one-surrogate perturbation (OFT) matches or exceeds the expensive optimization-based attack in 11 of 12 tested configurations.
Certifiably Robust Image Watermark
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns and has been widely deployed in industry. However, watermarking is vulnerable to removal attacks and forgery attacks. In this work, we propose the first image watermarks with certified robustness guarantees against removal and forgery attacks. Our method leverages randomized smoothing, a popular technique to build certifiably robust classifiers and regression models. Our major technical contributions include extending randomized smoothing to watermarking by considering its unique characteristics, deriving the certified robustness guarantees, and designing algorithms to estimate them. Moreover, we extensively evaluate our image watermarks in terms of both certified and empirical robustness. Our code is available at \url{https://github.com/zhengyuan-jiang/Watermark-Library}.
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
The Efficacy of Transfer-based No-box Attacks on Image Watermarking: A Pragmatic Analysis
Transfer-based no-box watermark evasion largely fails without aligned surrogate models, and a simple one-surrogate perturbation (OFT) matches or exceeds the expensive optimization-based attack in 11 of 12 tested configurations.