ML Security PapersCTForensics: A Comprehensive Dataset and Method for AI-Generated CT Image Detection
Yiheng Li 1,2, Zichang Tan 3, Guoqing Xu 1,2, Yijun Ye 1,2, Yang Yang 1,2, Zhen Lei 1,2,2
Published on arXiv
2603.01878
Output Integrity Attack
OWASP ML Top 10 — ML09
Key Finding
ESF-CTFD consistently outperforms state-of-the-art natural-image forgery detectors on the CTForensics benchmark, with superior generalization across unseen CT generative models.
ESF-CTFD (Enhanced Spatial-Frequency CT Forgery Detector)
Novel technique introduced
With the rapid development of generative AI in medical imaging, synthetic Computed Tomography (CT) images have demonstrated great potential in applications such as data augmentation and clinical diagnosis, but they also introduce serious security risks. Despite the increasing security concerns, existing studies on CT forgery detection are still limited and fail to adequately address real-world challenges. These limitations are mainly reflected in two aspects: the absence of datasets that can effectively evaluate model generalization to reflect the real-world application requirements, and the reliance on detection methods designed for natural images that are insensitive to CT-specific forgery artifacts. In this view, we propose CTForensics, a comprehensive dataset designed to systematically evaluate the generalization capability of CT forgery detection methods, which includes ten diverse CT generative methods. Moreover, we introduce the Enhanced Spatial-Frequency CT Forgery Detector (ESF-CTFD), an efficient CNN-based neural network that captures forgery cues across the wavelet, spatial, and frequency domains. First, it transforms the input CT image into three scales and extracts features at each scale via the Wavelet-Enhanced Central Stem. Then, starting from the largest-scale features, the Spatial Process Block gradually performs feature fusion with the smaller-scale ones. Finally, the Frequency Process Block learns frequency-domain information for predicting the final results. Experiments demonstrate that ESF-CTFD consistently outperforms existing methods and exhibits superior generalization across different CT generative models.
Key Contributions
- CTForensics dataset covering 10 diverse CT generative methods (4 GAN-based, 6 diffusion-based) specifically designed to evaluate generalization of forgery detection to unseen generators
- ESF-CTFD: a CNN-based detector exploiting wavelet, spatial, and frequency domains via Wavelet-Enhanced Central Stem, Spatial Process Block, and Frequency Process Block tailored for CT-specific forgery artifacts
- Demonstrates consistent outperformance over existing natural-image-based forgery detectors on cross-generative-model generalization benchmarks
🛡️ Threat Analysis
The paper's primary contributions are detecting AI-generated (synthetic) CT images and a dataset for evaluating such detection — squarely within ML09's scope of AI-generated content detection and output integrity verification. The ESF-CTFD is a novel forensic architecture, not a mere domain application of an existing detector.