Fraternal Twins: Unifying Attacks on Machine Learning and Digital Watermarking

TL;DR

This paper unifies attack and defense strategies in machine learning and digital watermarking, revealing their similarities and enabling cross-application of security techniques to enhance robustness in both fields.

Contribution

It introduces a unified notation for black-box attacks, demonstrating how watermarking defenses can improve machine learning security and vice versa.

Findings

Watermarking countermeasures can mitigate model-extraction attacks.

Machine learning hardening techniques can defend against watermark oracle attacks.

Unified framework reveals deep similarities between the two fields.

Abstract

Machine learning is increasingly used in security-critical applications, such as autonomous driving, face recognition and malware detection. Most learning methods, however, have not been designed with security in mind and thus are vulnerable to different types of attacks. This problem has motivated the research field of adversarial machine learning that is concerned with attacking and defending learning methods. Concurrently, a different line of research has tackled a very similar problem: In digital watermarking information are embedded in a signal in the presence of an adversary. As a consequence, this research field has also extensively studied techniques for attacking and defending watermarking methods. The two research communities have worked in parallel so far, unnoticeably developing similar attack and defense strategies. This paper is a first effort to bring these communities together. To this end, we present a unified notation of black-box attacks against machine learning and watermarking that reveals the similarity of both settings. To demonstrate the efficacy of this unified view, we apply concepts from watermarking to machine learning and vice versa. We show that countermeasures from watermarking can mitigate recent model-extraction attacks and, similarly, that techniques for hardening machine learning can fend off oracle attacks against watermarks. Our work provides a conceptual link between two research fields and thereby opens novel directions for improving the security of both, machine learning and digital watermarking.