Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attacks

TL;DR

This paper examines the vulnerabilities of AI-generated face detection systems to adversarial attacks and proposes a combined approach of adversarial training and diffusion-based reconstruction to improve robustness.

Contribution

It introduces a novel method integrating adversarial training with diffusion inversion to enhance detection robustness against adversarial examples.

Findings

Existing detectors are vulnerable to adversarial perturbations.

The proposed method significantly improves robustness against adversarial attacks.

Code will be publicly available for further research.

Abstract

The rapid advancement of generative image technology has introduced significant security concerns, particularly in the domain of face generation detection. This paper investigates the vulnerabilities of current AI-generated face detection systems. Our study reveals that while existing detection methods often achieve high accuracy under standard conditions, they exhibit limited robustness against adversarial attacks. To address these challenges, we propose an approach that integrates adversarial training to mitigate the impact of adversarial examples. Furthermore, we utilize diffusion inversion and reconstruction to further enhance detection robustness. Experimental results demonstrate that minor adversarial perturbations can easily bypass existing detection systems, but our method significantly improves the robustness of these systems. Additionally, we provide an in-depth analysis of adversarial and benign examples, offering insights into the intrinsic characteristics of AI-generated content. All associated code will be made publicly available in a dedicated repository to facilitate further research and verification.