Survey on AI-Generated Media Detection: From Non-MLLM to MLLM

TL;DR

This survey reviews the evolution of AI-generated media detection methods, comparing non-MLLM and MLLM approaches, analyzing their methodologies, challenges, and ethical considerations to guide future research.

Contribution

It provides the first comprehensive comparison of non-MLLM and MLLM-based detection methods, analyzing their differences, potential hybrids, and addressing ethical and regulatory issues.

Findings

MLLM-based detectors offer broader applicability and explainability.

Hybrid approaches show promise in improving detection accuracy.

Regulatory landscapes vary significantly across jurisdictions.

Abstract

The proliferation of AI-generated media poses significant challenges to information authenticity and social trust, making reliable detection methods highly demanded. Methods for detecting AI-generated media have evolved rapidly, paralleling the advancement of Multimodal Large Language Models (MLLMs). Current detection approaches can be categorized into two main groups: Non-MLLM-based and MLLM-based methods. The former employs high-precision, domain-specific detectors powered by deep learning techniques, while the latter utilizes general-purpose detectors based on MLLMs that integrate authenticity verification, explainability, and localization capabilities. Despite significant progress in this field, there remains a gap in literature regarding a comprehensive survey that examines the transition from domain-specific to general-purpose detection methods. This paper addresses this gap by providing a systematic review of both approaches, analyzing them from single-modal and multi-modal perspectives. We present a detailed comparative analysis of these categories, examining their methodological similarities and differences. Through this analysis, we explore potential hybrid approaches and identify key challenges in forgery detection, providing direction for future research. Additionally, as MLLMs become increasingly prevalent in detection tasks, ethical and security considerations have emerged as critical global concerns. We examine the regulatory landscape surrounding Generative AI (GenAI) across various jurisdictions, offering valuable insights for researchers and practitioners in this field.