SurFITR: A Dataset for Surveillance Image Forgery Detection and Localisation
This addresses the challenge of falsifying visual evidence in surveillance imagery, which is critical for security and forensic applications, but it is incremental as it focuses on dataset creation rather than a new detection method.
The paper tackles the problem of detecting and localising image forgeries in surveillance scenarios, where existing methods struggle due to subtle, localised tampering, and introduces the SurFITR dataset, which improves detector performance with over 137k tampered images and shows substantial gains in in-domain and cross-domain evaluations.
We present the Surveillance Forgery Image Test Range (SurFITR), a dataset for surveillance-style image forgery detection and localisation, in response to recent advances in open-access image generation models that raise concerns about falsifying visual evidence. Existing forgery models, trained on datasets with full-image synthesis or large manipulated regions in object-centric images, struggle to generalise to surveillance scenarios. This is because tampering in surveillance imagery is typically localised and subtle, occurring in scenes with varied viewpoints, small or occluded subjects, and lower visual quality. To address this gap, SurFITR provides a large collection of forensically valuable imagery generated via a multimodal LLM-powered pipeline, enabling semantically aware, fine-grained editing across diverse surveillance scenes. It contains over 137k tampered images with varying resolutions and edit types, generated using multiple image editing models. Extensive experiments show that existing detectors degrade significantly on SurFITR, while training on SurFITR yields substantial improvements in both in-domain and cross-domain performance. SurFITR is publicly available on GitHub.