Adversarial Attacks and Identity Leakage in De-Identification Systems: An Empirical Study

2026-09-22

AI Summary

研究了对抗攻击对去标识化系统中身份编码器的影响，并通过微调对抗样本和使用低通滤波器来缓解信息泄露问题。

Abstract

In this paper, we investigate the impact of adversarial attacks on identity encoders within a realistic de-identification framework. Our experiments show that the transferability of attacks transfers from an external surrogate model to the system model (e.g., CosFace to ArcFace) allows the adversary to cause identity information to leak in a sufficiently sensitive face recognition system. We present experimental evidence and propose strategies to mitigate this vulnerability. Specifically, we show how fine-tuning on adversarial examples helps to mitigate this effect for distortion-based attacks (i.e., snow, fog, etc.), while a simple low-pass filter can attenuate the effect of adversarial noise without affecting the de-identified images. Our mitigation results in a de-identification system that preserves its functionality while being significantly more robust to adversarial noise.

Problem

• Adversarial Attacks
• Identity Leakage
• De-Identification Systems
• Face Recognition

Innovation

• Adversarial Attacks
• Identity Leakage
• De-Identification Systems
• Fine-tuning on Adversarial Examples
• Low-pass Filter