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

arXiv:2609.27022 · cs.CV · Submitted 2026-09-22 · Read on arXiv

cs.CV

Submitted: 2026-09-22

Updated: 2026-09-22

Code: https://github.com/ddkang/advex-uar

License: http://creativecommons.org/licenses/by-sa/4.0/

The gist: In this paper, we investigate the impact of adversarial attacks on identity encoders within a realistic de-identification framework.

Terminology

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.

Sources

Related papers