Lijia Yu

neural network (3) adversarial example (2) adversarial training (2) adversarial attack (2) data augmentation (2) model architecture (1) privacy preservation (1) responsible ai (1) corruption robustness (1) out-of-distribution generalization (1) backdoor attack (1) generative model (1) safety evaluation (1) generative ai (1) neural network robustness (1) frequency domain (1) text-to-video generation (1) video safety benchmark (1) jailbreak attack (1) safety benchmark (1)