Attention-aggregated Attack for Boosting the Transferability of Facial Adversarial Examples

TL;DR

This paper introduces Attention-aggregated Attack (AAA), a novel method to improve the transferability of adversarial examples in face recognition models by targeting model-specific facial features through attention divergence.

Contribution

The paper proposes a new attack method, AAA, that enhances transferability by mimicking and disrupting facial feature attentions across different face recognition models.

Findings

AAA outperforms existing attack methods in transferability.

The method effectively targets model-specific facial features.

Experiments validate AAA's robustness across various FR models.

Abstract

Adversarial examples have revealed the vulnerability of deep learning models and raised serious concerns about information security. The transfer-based attack is a hot topic in black-box attacks that are practical to real-world scenarios where the training datasets, parameters, and structure of the target model are unknown to the attacker. However, few methods consider the particularity of class-specific deep models for fine-grained vision tasks, such as face recognition (FR), giving rise to unsatisfactory attacking performance. In this work, we first investigate what in a face exactly contributes to the embedding learning of FR models and find that both decisive and auxiliary facial features are specific to each FR model, which is quite different from the biological mechanism of human visual system. Accordingly we then propose a novel attack method named Attention-aggregated Attack (AAA) to enhance the transferability of adversarial examples against FR, which is inspired by the attention divergence and aims to destroy the facial features that are critical for the decision-making of other FR models by imitating their attentions on the clean face images. Extensive experiments conducted on various FR models validate the superiority and robust effectiveness of the proposed method over existing methods.