Face Reconstruction Transfer Attack as Out-of-Distribution Generalization

TL;DR

This paper introduces a novel face reconstruction transfer attack method that generalizes across unseen face recognition encoders by framing it as an out-of-distribution problem and proposing ALSUV for robust attack reconstruction.

Contribution

It formulates face reconstruction transfer attack as an OOD problem and proposes ALSUV, a new method combining latent search, trajectory averaging, and unsupervised validation for better generalization.

Findings

Effective transfer attack on unseen encoders

Outperforms baseline methods in generalization

Validated on multiple face datasets

Abstract

Understanding the vulnerability of face recognition systems to malicious attacks is of critical importance. Previous works have focused on reconstructing face images that can penetrate a targeted verification system. Even in the white-box scenario, however, naively reconstructed images misrepresent the identity information, hence the attacks are easily neutralized once the face system is updated or changed. In this paper, we aim to reconstruct face images which are capable of transferring face attacks on unseen encoders. We term this problem as Face Reconstruction Transfer Attack (FRTA) and show that it can be formulated as an out-of-distribution (OOD) generalization problem. Inspired by its OOD nature, we propose to solve FRTA by Averaged Latent Search and Unsupervised Validation with pseudo target (ALSUV). To strengthen the reconstruction attack on OOD unseen encoders, ALSUV reconstructs the face by searching the latent of amortized generator StyleGAN2 through multiple latent optimization, latent optimization trajectory averaging, and unsupervised validation with a pseudo target. We demonstrate the efficacy and generalization of our method on widely used face datasets, accompanying it with extensive ablation studies and visually, qualitatively, and quantitatively analyses. The source code will be released.