TL;DR
TGIF2 is an extended dataset and benchmark for evaluating the robustness of media forensic methods against modern text-guided inpainting and AI-based image enhancements, revealing limitations in current techniques.
Contribution
It introduces TGIF2, an updated dataset with recent inpainting models and non-semantic masks, enabling comprehensive forensic evaluation and analysis of current challenges.
Findings
Both IFL and SID methods degrade on FLUX.1 manipulations.
Fine-tuning improves localization but reveals object bias.
Super-resolution weakens forensic traces significantly.
Abstract
Generative AI has made text-guided inpainting a powerful image editing tool, but at the same time a growing challenge for media forensics. Existing benchmarks, including our text-guided inpainting forgery (TGIF) dataset, show that image forgery localization (IFL) methods can localize manipulations in spliced images but struggle not in fully regenerated (FR) images, while synthetic image detection (SID) methods can detect fully regenerated images but cannot perform localization. With new generative inpainting models emerging and the open problem of localization in FR images remaining, updated datasets and benchmarks are needed. We introduce TGIF2, an extended version of TGIF, that captures recent advances in text-guided inpainting and enables a deeper analysis of forensic robustness. TGIF2 augments the original dataset with edits generated by FLUX.1 models, as well as with random…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
