Rescind: 通过视觉-语言和状态空间建模对抗生物医学出版物中的图像不当行为
Rescind: Countering Image Misconduct in Biomedical Publications with Vision-Language and State-Space Modeling
AI总结：
Rescind通过视觉-语言和状态空间建模方法，提出首个生物医学图像伪造生成与检测框架，实现高精度伪造定位与验证。
摘要：
生物医学出版物中的科学图像篡改正对研究完整性和可重复性构成日益严重的威胁。与自然图像取证不同，生物医学伪造检测具有独特挑战，因为存在领域特定的伪影、复杂的纹理和无结构的图表布局。我们提出了第一个视觉-语言引导的框架，用于生成和检测生物医学图像伪造。通过结合基于扩散的合成与视觉-语言提示，我们的方法能够实现逼真且语义可控的操纵，包括复制、拼接和区域移除，适用于多种生物医学模式。我们介绍了Rescind，一个大规模基准，包含细粒度标注和模态特定的划分，并提出了Integscan，一个结构化的状态空间建模框架，整合了增强注意力的视觉编码与提示条件的语义对齐，以实现精确的伪造定位。为确保语义忠实性，我们引入了一个基于视觉-语言模型的验证循环，用于过滤生成的伪造，以确保其与预期提示的一致性。在Rescind和现有基准上的广泛实验表明，Integscan在检测和定位方面均实现了最先进的性能，为自动化科学完整性分析奠定了坚实基础。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
