Xinlei He

jailbreak attack (2) adversarial attack (2) backdoor attack (2) representation learning (1) adversarial learning (1) model security (1) stochastic gradient descent (1) transfer learning (1) pose estimation (1) text classification (1) graph classification (1) object detection (1) model robustness (1) self-supervised learning (1) question answering (1) social media analysis (1) deepfake detection (1) deep learning (1) multilingual text (1) data poisoning (1)