Discriminative AI
- Rounding-Guided Backdoor Injection in Deep Learning Model Quantization, NDSS 2026Feb 2026
- Towards Provably Unlearnable Examples via Bayes Error Optimization, AAAI 2026Jan 2026
- Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks, TDSC 2026Jan 2026
- Democratic Training Against Universal Adversarial Perturbations, ICLR 2025Apr 2025
- Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning, TIFS 2025Jun 2025
- Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors, CAV 2024Jul 2024
- Certified Continual Learning for Neural Network Regression, ISSTA 2024Sept 2024
- Neural Network Semantic Backdoor Detection and Mitigation: A Causality-Based Approach, USENIX Security 2024Aug 2024
- Certified Quantization Strategy Synthesis for Neural Networks, FM 2024Sept 2024
