A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization

TL;DR

This survey reviews AI-generated text forensic systems, focusing on detection, attribution, and characterization, highlighting current efforts, resources, challenges, and future directions in combating misuse of LLMs.

Contribution

It provides a comprehensive taxonomy and overview of existing AI-generated text forensic methods, emphasizing the three key pillars and future research directions.

Findings

Existing forensic systems focus on detection, attribution, and characterization.

Resources and datasets are available for research in AI-generated text forensics.

Challenges include evolving LLM capabilities and the need for robust detection methods.

Abstract

We have witnessed lately a rapid proliferation of advanced Large Language Models (LLMs) capable of generating high-quality text. While these LLMs have revolutionized text generation across various domains, they also pose significant risks to the information ecosystem, such as the potential for generating convincing propaganda, misinformation, and disinformation at scale. This paper offers a review of AI-generated text forensic systems, an emerging field addressing the challenges of LLM misuses. We present an overview of the existing efforts in AI-generated text forensics by introducing a detailed taxonomy, focusing on three primary pillars: detection, attribution, and characterization. These pillars enable a practical understanding of AI-generated text, from identifying AI-generated content (detection), determining the specific AI model involved (attribution), and grouping the underlying intents of the text (characterization). Furthermore, we explore available resources for AI-generated text forensics research and discuss the evolving challenges and future directions of forensic systems in an AI era.