As automated attack techniques rapidly advance, CAPTCHAs remain a critical defense mechanism against malicious bots. However, existing CAPTCHA schemes encompass a diverse range of modalities—from static distorted text and obfuscated images to interactive clicks, sliding puzzles, and logic-based questions—yet the community still lacks a unified, large-scale, multimodal benchmark to rigorously evaluate their security robustness. To address this gap, we introduce MCA-Bench, a comprehensive and reproducible benchmarking suite that integrates heterogeneous CAPTCHA types into a single evaluation protocol. Leveraging a shared vision–language model backbone, we fine-tune specialized cracking agents for each CAPTCHA category, enabling consistent, cross-modal assessments. Extensive experiments reveal that MCA-Bench effectively maps the vulnerability spectrum of modern CAPTCHA designs under varied attack settings, and—crucially—offers the first quantitative analysis of how challenge complexity, interaction depth, and model solvability interrelate. Based on these findings, we propose three actionable design principles and identify key open challenges, laying the groundwork for systematic CAPTCHA hardening, fair benchmarking, and broader community collaboration.

Medical semantic-mask synthesis enhances data augmentation and analysis, yet most GAN-based methods still generate one-to-one images without maintaining spatial consistency across slices. To overcome this, we propose AnatoMaskGAN, a novel framework that embeds interslice spatial features, integrates diverse augmentation strategies, and optimizes deep feature learning for complex medical scans. Specifically, a GNN-based slice-feature fusion module models spatial relationships and aggregates contextual cues from neighboring slices, capturing anatomical structures more comprehensively. A 3D spatial noise-injection strategy fuses weighted spatial features with noise to enrich structural diversity, while a grayscale-texture classifier refines grayscale and texture representation during generation. Experiments on L2R-OASIS and L2R-Abdomen CT show that AnatoMaskGAN achieves 26.50 dB PSNR and 0.9229 SSIM on L2R-OASIS, surpassing the state of the art by 0.43 dB, and reaches 0.8602 SSIM on L2R-Abdomen CT, a 0.48-point improvement. Ablation studies confirm that removing any of the three modules degrades PSNR, SSIM, and LPIPS, verifying the effectiveness of each component in enhancing reconstruction fidelity and perceptual quality. Code is available at https://github.com/noheadwuzonglin/AnatoMaskGAN.

The rapid development of traffic theory and information technology has provided diversified and large-scale traffic data resources for traffic research and urban traffic management. At the same time, these data also present many challenges, such as missing data and deviations in data collection. Many researchers have reported that inaccurate or incomplete measurements of traffic variables can be corrected based on either traditional traffic flow theory, which ignores the randomness of traffic, or are performed using machine learning methods, which emphasize data quantity, but do not make effective use of domain knowledge. This paper proposes a Traffic Factor State Network framework defined by traffic factors and their links to represent the relationships between traffic factors; this framework includes not only obvious traffic factors like volume and speed, but also hidden traffic factors such as the environmental impact factor, which is a variable used to represent complex road conditions. This variable is used to describe the influence of non-traffic flow parameters such as road condition and environmental factors, and is estimated by the EM (Expectation Maximization) algorithm based on historical data. This study used a high-order multivariate Markov model to implement the TFSN, which was then used to establish a stochastic model of speed and related factors. A large amount of historical data was used to calculate and calibrate the strength of the links between the model factors. Finally, a stochastic model of speed prediction was established. The verification results compared with actual cases demonstrate the validity and applicability of the proposed model.