識別型 AI
- Rounding-Guided Backdoor Injection in Deep Learning Model Quantization, NDSS 20262026年2月
- Towards Provably Unlearnable Examples via Bayes Error Optimization, AAAI 20262026年1月
- Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks, TDSC 20262026年1月
- Democratic Training Against Universal Adversarial Perturbations, ICLR 20252025年4月
- Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning, TIFS 20252025年6月
- Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors, CAV 20242024年7月
- Certified Continual Learning for Neural Network Regression, ISSTA 20242024年9月
- Neural Network Semantic Backdoor Detection and Mitigation: A Causality-Based Approach, USENIX Security 20242024年8月
- Certified Quantization Strategy Synthesis for Neural Networks, FM 20242024年9月
