Protecting AI content with deep watermarks

Paper Title:

Investigating Deep Watermark Security: An Adversarial Transferability Perspective

Published on:

26 February 2024

Primary Category:

Cryptography and Security

Paper Authors:

Biqing Qi,

Junqi Gao,

Yiang Luo,

Jianxing Liu,

Ligang Wu,

Bowen Zhou

Bullets

Key Details

•

Deep watermarks can protect IP in AI content but face security risks

•

Proposed ESMA and BEM-ESMA reliably attack deep watermarks

•

Increasing robustness to transformations lowers security

•

Longer watermark encodings are more prone to erasure attacks

•

Study is first to systematically assess deep watermark risks

Explore the topics in this paper

adversarial-attacks

deep-learning

information-security

intellectual-property

model-robustness

AI generated summary

Protecting AI content with deep watermarks

This paper explores using deep watermarks to protect intellectual property in AI-generated content. It finds current methods vulnerable to erasure and tampering through adversarial attacks. To evaluate this, the authors propose two new targeted attack methods, ESMA and BEM-ESMA. Experiments show these reliably compromise deep watermarks by either erasing or manipulating them. The study considers different model architectures and watermark encoding lengths, finding tradeoffs between transformation robustness and security. Overall it systematically assesses deep watermark risks and aims to spur research into more robust techniques.