arXiv:2603. 18577v2 Announce Type: replace Abstract: Text-guided image editors can now manipulate authentic medical scans with high fidelity, enabling lesion implantation/removal that threatens clinical trust and safety.
arXiv:2609.39066v1 Announce Type: new Abstract: Conventional image forgery detection methods produce binary scores or pixel-level masks without interpretable evidence, while recent multimodal large l...
arXiv:2605.16080v2 Announce Type: replace Abstract: The rise of AI-generated images (AIGIs) poses growing challenges for digital authenticity, prompting the need for efficient, generalizable image fo...
arXiv:2606. 14697v1 Announce Type: cross Abstract: Building trustworthy medical multimodal large language models (MLLMs) is critical for reliable clinical decision support.
With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored vision-language model (VLM)-based synthetic image detection, these evaluations typically consider images in isolation.
arXiv:2608. 06865v1 Announce Type: cross Abstract: The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety.
arXiv:2606. 25375v2 Announce Type: replace-cross Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud.
arXiv:2601.06847v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) can generate convincing clinical narratives, yet frequently struggle to visually ground their statements. We po...
MedFabric is a new benchmark for detecting word‑level medical fabrications, comprising 646 fabricated statements each paired with a ground‑truth passage that shares the same LLM authorship and nearly identical wording. The study shows that current detectors perform poorly—expert clinicians achieve only 53.3% macro‑F1 and no detector family surpasses 60% without gold evidence—highlighting that detection hinges on evidence correctness rather than subtlety of fabrication. The authors demonstrate that a retrieval‑confidence gate can substantially improve performance, raising macro‑F1 from 61% to 74%.
PathPocket is a multimodal AI co‑pilot that grounds pathology decision‑making in evidence. It builds the largest pathology evidence corpus (≈110,472 documents) and a hypergraph of 4.55 million entities and 7.10 million relations to support traceable reasoning. The system handles text and multimodal queries, including ROI and gigapixel whole‑slide images, and outperforms current state‑of‑the‑art models on a benchmark of over 200,000 real‑world cases, improving pathologists’ diagnostic accuracy and confidence.
arXiv:2604. 02694v2 Announce Type: replace-cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety.
The paper introduces an evidence‑guided detector‑localizer‑reasoner system for text‑centric image forensics, addressing the challenges posed by AI‑generated content. It combines an image‑level authenticity detector, a localizer that extracts tampered regions, and an MLLM‑based reasoner that generates structured forensic reports grounded in the detected evidence. The system employs iterative difficulty‑aware mining and report‑mask consistency post‑processing, achieving a score of 0.638 and ranking second in the ACM Multimedia 2026 GenText‑Forensics Challenge.
arXiv:2606. 17958v1 Announce Type: cross Abstract: Semi-supervised medical image segmentation has emerged as a dominant research problem in medical image analysis, mitigating annotation scarcity by leveraging consistency regularization on unlabeled data.