Adversarial Magnification to Deceive Deepfake Detection through Super Resolution

TL;DR

This paper introduces a novel adversarial attack method using super resolution techniques to deceive deepfake detection systems, revealing their vulnerability to minimal visual modifications.

Contribution

It proposes a new black-box attack leveraging super resolution to significantly impair deepfake detectors' accuracy, a novel approach in adversarial attacks against media forensics.

Findings

Super resolution can drastically reduce deepfake detection accuracy.

Minimal visual changes can deceive detection systems effectively.

The attack is quick, black-box, and highly effective.

Abstract

Deepfake technology is rapidly advancing, posing significant challenges to the detection of manipulated media content. Parallel to that, some adversarial attack techniques have been developed to fool the deepfake detectors and make deepfakes even more difficult to be detected. This paper explores the application of super resolution techniques as a possible adversarial attack in deepfake detection. Through our experiments, we demonstrate that minimal changes made by these methods in the visual appearance of images can have a profound impact on the performance of deepfake detection systems. We propose a novel attack using super resolution as a quick, black-box and effective method to camouflage fake images and/or generate false alarms on pristine images. Our results indicate that the usage of super resolution can significantly impair the accuracy of deepfake detectors, thereby highlighting the vulnerability of such systems to adversarial attacks. The code to reproduce our experiments is available at: https://github.com/davide-coccomini/Adversarial-Magnification-to-Deceive-Deepfake-Detection-through-Super-Resolution