DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

TL;DR

This paper introduces DP-TRAE, a dual-phase reversible adversarial attack method that enhances transferability and effectiveness in black-box scenarios for image privacy protection, achieving high success and recovery rates.

Contribution

The paper proposes a novel dual-phase merging strategy that improves transferability of reversible adversarial examples in black-box settings, addressing limitations of prior white-box focused methods.

Findings

Achieves 99.0% attack success rate in black-box scenarios

Attains 100% recovery rate for reversible examples

Successfully attacks a commercial model demonstrating practical applicability

Abstract

In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural Networks (DNNs). However, existing RAE techniques primarily focus on white-box attacks, lacking a comprehensive evaluation of their effectiveness in black-box scenarios. This limitation impedes their broader deployment in complex, dynamic environments. Further more, traditional black-box attacks are often characterized by poor transferability and high query costs, significantly limiting their practical applicability. To address these challenges, we propose the Dual-Phase Merging Transferable Reversible Attack method, which generates highly transferable initial adversarial perturbations in a white-box model and employs a memory augmented black-box strategy to effectively mislead target mod els. Experimental results demonstrate the superiority of our approach, achieving a 99.0% attack success rate and 100% recovery rate in black-box scenarios, highlighting its robustness in privacy protection. Moreover, we successfully implemented a black-box attack on a commercial model, further substantiating the potential of this approach for practical use.