EvolveReason: Self-Evolving Reasoning Paradigm for Explainable Deepfake Facial Image Identification

TL;DR

EvolveReason is a novel self-evolving reasoning framework for deepfake facial image identification that mimics human reasoning, improves explainability, and enhances detection accuracy through a chain-of-thought dataset, latent-space analysis, and reinforcement learning.

Contribution

It introduces a human-like reasoning paradigm with a chain-of-thought dataset, forgery latent-space analysis, and self-evolution strategies to improve deepfake detection and explanation.

Findings

Outperforms state-of-the-art in detection accuracy

Provides detailed forgery explanations

Demonstrates strong generalization capabilities

Abstract

With the rapid advancement of AIGC technology, developing identification methods to address the security challenges posed by deepfakes has become urgent. Face forgery identification techniques can be categorized into two types: traditional classification methods and explainable VLM approaches. The former provides classification results but lacks explanatory ability, while the latter, although capable of providing coarse-grained explanations, often suffers from hallucinations and insufficient detail. To overcome these limitations, we propose EvolveReason, which mimics the reasoning and observational processes of human auditors when identifying face forgeries. By constructing a chain-of-thought dataset, CoT-Face, tailored for advanced VLMs, our approach guides the model to think in a human-like way, prompting it to output reasoning processes and judgment results. This provides practitioners with reliable analysis and helps alleviate hallucination. Additionally, our framework incorporates a forgery latent-space distribution capture module, enabling EvolveReason to identify high-frequency forgery cues difficult to extract from the original images. To further enhance the reliability of textual explanations, we introduce a self-evolution exploration strategy, leveraging reinforcement learning to allow the model to iteratively explore and optimize its textual descriptions in a two-stage process. Experimental results show that EvolveReason not only outperforms the current state-of-the-art methods in identification performance but also accurately identifies forgery details and demonstrates generalization capabilities.