Trustworthy Image Authentication using Forensic Knowledge Graphs

2026-06-22

AI Summary

This work addresses the limited interpretability of existing image forgery detection methods and the inability of vision-language models to effectively leverage forensic traces for reliable authentication. To bridge this gap, the authors propose the Forensic Knowledge Graph (FKG) framework, which uniquely unifies forensic traces, causal dependencies, and scene content within a single structured representation. An iterative context refinement strategy is introduced to guide vision-language models in generating faithful and human-interpretable explanations. The proposed approach significantly outperforms state-of-the-art methods across multiple tasks, including forgery detection, manipulation type identification, localization, and explanation generation. To support further research, the authors also release FKG-50K, a large-scale dataset comprising 50,000 annotated samples.

Abstract

Advances in generative AI have made image falsification highly realistic, demanding trustworthy authentication systems. Existing forensic detectors can target certain forgery types but lack interpretability, while vision-language models (VLMs) provide explanations but cannot exploit forensic traces for reliable detection. We propose Forensic Knowledge Graphs (FKGs), a unified framework that integrates forensic evidence extraction, structured reasoning, and human-interpretable explanation. Our FKG structure encodes forensic traces along with their causal dependencies and links to scene content. To generate accurate FKGs, we introduce a novel forensic authentication network and an Iterative Context Refinement strategy that guides VLMs to produce faithful, grounded explanations. We also present FKG-50K, a dataset of 50,000 realistic forgeries with ground-truth FKGs. Experiments demonstrate that FKG outperforms both forensic detectors and VLMs in detection, forgery identification and localization, and forensic justification.

Problem

• image authentication
• forensic detection
• generative AI
• interpretability
• forgery localization

Innovation

• Forensic Knowledge Graphs
• Interpretable AI
• Image Forgery Detection
• Vision-Language Models
• Iterative Context Refinement