Menu

News

最新消息

2024-12-23
【專題演講】113/12/23(一) 11:00-11:50 Dr. Qifan Song

Adversarial vulnerability is the Achilles' Heel of modern deep learning. Understanding the mechanisms of adversarial attacks for deep learning helps researchers improve the trustworthiness of artificial intelligence. In this talk, we establish a connection between adversarial robustness and data geometry under the manifold hypothesis and identify some fundamental source of adversarial vulnerabilities.