Detecting and Segmenting Adversarial Graphics Patterns from Images

TL;DR

This paper addresses the challenge of detecting and segmenting artificial graphics patterns in images to defend against malicious uploads, proposing a new segmentation method that outperforms existing algorithms.

Contribution

The paper formulates the problem as graphics pattern segmentation and introduces a novel method tailored for this task, demonstrating superior performance over baseline algorithms.

Findings

The proposed method outperforms baseline segmentation algorithms.

The method shows strong generalization to different artificial graphics patterns.

Extensive experiments validate the effectiveness of the approach.

Abstract

Adversarial attacks pose a substantial threat to computer vision system security, but the social media industry constantly faces another form of "adversarial attack" in which the hackers attempt to upload inappropriate images and fool the automated screening systems by adding artificial graphics patterns. In this paper, we formulate the defense against such attacks as an artificial graphics pattern segmentation problem. We evaluate the efficacy of several segmentation algorithms and, based on observation of their performance, propose a new method tailored to this specific problem. Extensive experiments show that the proposed method outperforms the baselines and has a promising generalization capability, which is the most crucial aspect in segmenting artificial graphics patterns.