3 papers
cs.LG2025
Scalable and Precise Patch Robustness Certification for Deep Learning Models with Top-k Predictions
Qilin Zhou, Haipeng Wang, Zhengyuan Wei +1
Patch robustness certification is an emerging verification approach for defending against adversarial patch attacks with provable guarantees for deep learning systems. Certified re…
cs.SE2024
A3Rank: Augmentation Alignment Analysis for Prioritizing Overconfident Failing Samples for Deep Learning Models
Zhengyuan Wei, Haipeng Wang, Qilin Zhou +1
Sharpening deep learning models by training them with examples close to the decision boundary is a well-known best practice. Nonetheless, these models are still error-prone in prod…
cs.SE2023
A study on the impact of pre-trained model on Just-In-Time defect prediction
Yuxiang Guo, Xiaopeng Gao, Zhenyu Zhang +2
Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relatio…