The paper demonstrates that diffusion‑based inpainting introduces a subtle, global spectral shift across the entire image, which current AI‑generated image detectors fail to detect. By creating a model‑free diagnostic called Inpainting Exchange (INP‑X) that restores unedited pixels while keeping synthesized content, the authors show that many pretrained detectors, commercial APIs, and bias‑aware methods collapse to chance performance. A large benchmark of 30K triplets across four datasets and three inpainters confirms the prevalence of this artifact, and a perceptual study indicates humans also struggle to spot the shift.
By Elif Nebioglu, Emirhan Bilgi\c{c}, Adrian Popescu
arXiv:2605.16879v2 Announce Type: replace
Abstract: With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for...
By Yunfei Wang, Bo Du, Zhe Yang, Xin Liu, Zhiyu Lin, Tianxin Xu, Ji-Zhe Zhou
The paper introduces VITA, a multi‑source vicinal transfer augmentation method designed to improve out‑of‑distribution generalization in computer vision. VITA combines tangent transfer, which generates initial augmented samples to enhance robustness against various image corruptions, with an integration step that uses a generative model to produce on‑manifold samples from multiple vicinal sources. Experiments on corruption benchmarks show that VITA outperforms existing state‑of‑the‑art augmentation techniques.
By Minghui Chen, Cheng Wen, Feng Zheng, Fengxiang He, Ling Shao
The paper introduces the first systematic robustness benchmark for local invisible image watermarking, evaluating five methods across 55 image transformations that include signal distortions, coordinate misalignments, indirect local edits, and direct watermark edits. Results show that all methods are vulnerable to some transformation, with MaskWM achieving the best payload recovery and localization but at the cost of image quality. The study highlights that robustness varies strongly with transformation type, especially noting that geometric misalignment and generative local edits can completely disrupt payload recovery.
By Kai Yao, Bence Szil\'agyi, Sebesty\'en Kamp, M\'at\'e Po\'or, M\'at\'e Szilveszter, Matyas K. Zsoldos, Marc Juarez
arXiv:2412.03044v3 Announce Type: replace
Abstract: Video anomaly detection (VAD) is a vital yet complex open-set task in computer vision, commonly tackled through reconstruction-based methods. Howev...
By Xiaofeng Tan, Hongsong Wang, Xin Geng, Liang Wang
arXiv:2606. 02178v1 Announce Type: cross Abstract: Recent advancements in generative AI have led to image editing models capable of producing realistic forgeries that evade traditional image forgery localization methods, as these approaches depend on physical noise absent in synthetic data.
By Yiming Wang, Baiqi Wu, Qingming Li, Jiahao Chen, Tong Zhang, Shouling Ji
DRIFT is a black‑box attack that removes diffusion watermarks by combining partial forward diffusion with stochastic reverse resampling. It limits the source information available to a fixed‑depth recovery pipeline and uses stochastic reversal to explore alternative noise‑driven paths, refining fidelity only on updates rejected by the same verifier. Across nine watermarks, DRIFT achieves 98–100% attack success and the best image quality without requiring secret keys, verifier internals, or per‑image gradient optimization.
The paper introduces a structured‑prior‑guided diffusion inpainting framework that enhances traffic sign augmentation by incorporating semantic, appearance, and geometric priors through text prompts, vector templates, and ControlNet. It enforces physical consistency with colour and edge‑structure losses, achieving superior reconstruction fidelity and OCR accuracy compared to larger models. The synthetic data generated improves detection performance for rare traffic sign classes by up to 7.4× over a real‑data‑only baseline.
By Luo Li, Chongchong Huang, Jun Jia, Qiang Gao, Xinlong Liu, Gui Yang, Liang Cao
arXiv:2505.23462v2 Announce Type: replace
Abstract: Blind face restoration from low-quality images is a challenging task that requires not only high-fidelity image reconstruction, but also preservati...
By Runyi Li, Bin Chen, Jian Zhang, Radu Timofte
DRIFT is a black‑box attack that removes diffusion watermarks by deflecting the generative trajectory. It combines partial forward diffusion with stochastic reverse resampling to limit the source information available to a fixed‑depth recovery pipeline and to explore alternative noise‑driven paths. Across nine watermarks, DRIFT achieves 98–100% success while preserving image quality, without requiring secret keys, verifier internals, or per‑image gradient optimization.
By Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Yang Song, Jiaojiao Jiang
arXiv:2606. 28094v1 Announce Type: cross Abstract: Real-world object removal is challenging due to two key difficulties: the target object's non-local effects, such as shadows and reflections, which are difficult to model, and the fact that user-provided masks are often inaccurate or incomplete.
By Qinming Zhou, Chenxi Sun, Deyang Kong, Junhao He, Xiangheng Tang, Peike Yu, Haotian Wu, Leilei Cao, Linfeng Zhang
FUSED is a new framework that jointly detects and localizes AI-generated inpainting by combining low-level forensic cues with high-level semantic features through a sparsely-gated Mixture-of-Experts architecture. It predicts both an image-level manipulation score and a pixel-level mask of the inpainted region. On the OpenSDID cross-generator benchmark, FUSED outperforms existing methods, especially on unseen generators, and transfers effectively to the AutoSplice and CocoGlide benchmarks, doubling localization performance.
By Anton Nuzhdin, Marcel Worring, Ivona Najdenkoska