(Don't) Trust, but (Don't) Verify: Developers' Attention to Security in AI-Generated Code
研究通过观察100名参与者如何评估和选择AI生成的C语言代码的安全性和功能性,探讨了开发者在使用AI辅助编程时对安全性的关注程度及信任影响。
研究通过观察100名参与者如何评估和选择AI生成的C语言代码的安全性和功能性,探讨了开发者在使用AI辅助编程时对安全性的关注程度及信任影响。
针对多对比度MRI重建中数据不足的问题,提出基于内容/风格模型的CoSMo-RecNet框架,利用未配对图像数据学习共享表示,减少所需训练数据量。
研究通过生成合成缺陷样本和使用贝叶斯分类器解决制造中数据稀缺情况下的自动视觉检测信任问题。
This work addresses the degradation in image quality caused by k-space undersampling in unsupervised cine cardiac MRI reconstruction by proposing I-FP-INR, a novel image-domain dual-branch implicit neural representation framework. For the first time, an image feature embedding mechanism is integrated into implicit neural representations, enabling a backbone branch and a feature-processing branch to collaboratively learn complementary representations. This design enhances model expressiveness without requiring fully sampled reference data. By incorporating coil sensitivity encoding and an unsupervised learning strategy, I-FP-INR consistently outperforms existing baseline methods across multiple public and internal datasets, achieving superior reconstruction quality and demonstrating robust performance under varying sampling rates and diverse clinical scenarios.
This study addresses the lack of effective unsupervised monitoring tools for detecting anomalous behaviors in high-volume government procurement payments. The authors propose a Payment Heterogeneity Index (PHI) that integrates four dimensions—modality, asymmetry, tail behavior, and structural dispersion derived from a Gaussian Mixture Model (GMM)—thereby combining tail analysis with structural heterogeneity for the first time to uncover payment mechanism bifurcations overlooked by conventional metrics. Applied to municipal procurement data in the UK, PHI flagged 10.1% of suppliers as anomalous, exhibiting payment patterns markedly divergent from the norm; expert validation confirmed these cases warrant high investigative priority. Notably, PHI demonstrates distinct anomaly detection capability, showing low correlation with the coefficient of variation (ρ = 0.310).
研究通过观察100名参与者如何评估和选择AI生成的C语言代码的安全性和功能性,探讨了开发者在使用AI辅助编程时对安全性的关注程度及信任影响。
针对多对比度MRI重建中数据不足的问题,提出基于内容/风格模型的CoSMo-RecNet框架,利用未配对图像数据学习共享表示,减少所需训练数据量。
研究通过生成合成缺陷样本和使用贝叶斯分类器解决制造中数据稀缺情况下的自动视觉检测信任问题。
This work addresses the degradation in image quality caused by k-space undersampling in unsupervised cine cardiac MRI reconstruction by proposing I-FP-INR, a novel image-domain dual-branch implicit neural representation framework. For the first time, an image feature embedding mechanism is integrated into implicit neural representations, enabling a backbone branch and a feature-processing branch to collaboratively learn complementary representations. This design enhances model expressiveness without requiring fully sampled reference data. By incorporating coil sensitivity encoding and an unsupervised learning strategy, I-FP-INR consistently outperforms existing baseline methods across multiple public and internal datasets, achieving superior reconstruction quality and demonstrating robust performance under varying sampling rates and diverse clinical scenarios.
This study addresses the lack of effective unsupervised monitoring tools for detecting anomalous behaviors in high-volume government procurement payments. The authors propose a Payment Heterogeneity Index (PHI) that integrates four dimensions—modality, asymmetry, tail behavior, and structural dispersion derived from a Gaussian Mixture Model (GMM)—thereby combining tail analysis with structural heterogeneity for the first time to uncover payment mechanism bifurcations overlooked by conventional metrics. Applied to municipal procurement data in the UK, PHI flagged 10.1% of suppliers as anomalous, exhibiting payment patterns markedly divergent from the norm; expert validation confirmed these cases warrant high investigative priority. Notably, PHI demonstrates distinct anomaly detection capability, showing low correlation with the coefficient of variation (ρ = 0.310).