7 papers
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
Qilin Zhou, Zhengyuan Wei, Haipeng Wang +3
In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certification on such inputs within a patch bound can verify their…
Toward Patch Robustness Certification and Detection for Deep Learning Systems Beyond Consistent Samples
Qilin Zhou, Zhengyuan Wei, Haipeng Wang +2
Patch robustness certification is an emerging kind of provable defense technique against adversarial patch attacks for deep learning systems. Certified detection ensures the detect…
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…
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…
Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models
Haipeng Wang, Zhengyuan Wei, Qilin Zhou +1
In the testing-retraining pipeline for enhancing the robustness property of deep learning (DL) models, many state-of-the-art robustness-oriented fuzzing techniques are metric-orien…
CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models
Qilin Zhou, Zhengyuan Wei, Haipeng Wang +2
Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery…
A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models
Qilin Zhou, Zhengyuan Wei, Haipeng Wang +1
Patch robustness certification ensures no patch within a given bound on a sample can manipulate a deep learning model to predict a different label. However, existing techniques can…