Rescind: Countering Image Misconduct in Biomedical Publications with Vision-Language and State-Space Modeling

2026-01-12

AI Summary

This work addresses the critical threat posed by biomedical image manipulation to scientific integrity and reproducibility, which is exacerbated by domain-specific artifacts, complex textures, and unstructured layouts. To tackle these challenges, we propose the first unified vision–language framework for both controllable forgery generation and precise detection. Our approach leverages diffusion models guided by semantic prompts to synthesize realistic forgeries and introduces Integscan, a structured state-space model, for accurate tampering localization. We also construct Rescind, the first large-scale, fine-grained annotated benchmark for biomedical image integrity, and incorporate a semantic consistency verification mechanism to ensure alignment between generated content and textual prompts. Extensive experiments on Rescind and existing benchmarks demonstrate state-of-the-art performance in both detection and localization, establishing a new paradigm for automated scientific integrity analysis.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Intelligent Robots: Manipulation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Scientific image manipulation in biomedical publications poses a growing threat to research integrity and reproducibility. Unlike natural image forensics, biomedical forgery detection is uniquely challenging due to domain-specific artifacts, complex textures, and unstructured figure layouts. We present the first vision-language guided framework for both generating and detecting biomedical image forgeries. By combining diffusion-based synthesis with vision-language prompting, our method enables realistic and semantically controlled manipulations, including duplication, splicing, and region removal, across diverse biomedical modalities. We introduce Rescind, a large-scale benchmark featuring fine-grained annotations and modality-specific splits, and propose Integscan, a structured state space modeling framework that integrates attention-enhanced visual encoding with prompt-conditioned semantic alignment for precise forgery localization. To ensure semantic fidelity, we incorporate a vision-language model based verification loop that filters generated forgeries based on consistency with intended prompts. Extensive experiments on Rescind and existing benchmarks demonstrate that Integscan achieves state of the art performance in both detection and localization, establishing a strong foundation for automated scientific integrity analysis.

Problem

• scientific image manipulation
• biomedical image forgery
• research integrity
• image forensics
• reproducibility

Innovation

• vision-language modeling
• state-space modeling
• biomedical image forensics
• diffusion-based synthesis
• scientific integrity