VAAS: Vision-Attention Anomaly Scoring for Image Manipulation Detection in Digital Forensics
This addresses the challenge of verifying digital evidence authenticity for forensic investigators, though it is incremental as it builds on existing methods like Vision Transformers and SegFormer.
The paper tackled the problem of detecting AI-generated image forgeries in digital forensics by proposing VAAS, a dual-module framework that integrates global attention-based anomaly estimation with patch-level self-consistency scoring, achieving competitive F1 and IoU performance on datasets like DF2023 and CASIA v2.0.
Recent advances in AI-driven image generation have introduced new challenges for verifying the authenticity of digital evidence in forensic investigations. Modern generative models can produce visually consistent forgeries that evade traditional detectors based on pixel or compression artefacts. Most existing approaches also lack an explicit measure of anomaly intensity, which limits their ability to quantify the severity of manipulation. This paper introduces Vision-Attention Anomaly Scoring (VAAS), a novel dual-module framework that integrates global attention-based anomaly estimation using Vision Transformers (ViT) with patch-level self-consistency scoring derived from SegFormer embeddings. The hybrid formulation provides a continuous and interpretable anomaly score that reflects both the location and degree of manipulation. Evaluations on the DF2023 and CASIA v2.0 datasets demonstrate that VAAS achieves competitive F1 and IoU performance, while enhancing visual explainability through attention-guided anomaly maps. The framework bridges quantitative detection with human-understandable reasoning, supporting transparent and reliable image integrity assessment. The source code for all experiments and corresponding materials for reproducing the results are available open source.