A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication

TL;DR

This paper systematically reviews current defenses against AI-generated visual media, including detection, disruption, and authentication, highlighting methodologies, challenges, and future research directions in ensuring trustworthiness.

Contribution

It introduces a unified framework and taxonomy for defense strategies, summarizes evaluation datasets and metrics, and offers insights into research challenges and future directions.

Findings

Comprehensive taxonomy of defense methods

Analysis of robustness and fairness issues

Identification of key research challenges

Abstract

Deep generative models have demonstrated impressive performance in various computer vision applications, including image synthesis, video generation, and medical analysis. Despite their significant advancements, these models may be used for malicious purposes, such as misinformation, deception, and copyright violation. In this paper, we provide a systematic and timely review of research efforts on defenses against AI-generated visual media, covering detection, disruption, and authentication. We review existing methods and summarize the mainstream defense-related tasks within a unified passive and proactive framework. Moreover, we survey the derivative tasks concerning the trustworthiness of defenses, such as their robustness and fairness. For each defense strategy, we formulate its general pipeline and propose a multidimensional taxonomy applicable across defense tasks, based on methodological strategies. Additionally, we summarize the commonly used evaluation datasets, criteria, and metrics. Finally, by analyzing the reviewed studies, we provide insights into current research challenges and suggest possible directions for future research.