热点
"对抗性样本" 相关文章
When Images Fool AI Models
Communications of the ACM - Artificial Intelligence 2025-11-02T16:55:23.000000Z
A new way to test how well AI systems classify text
MIT News - Artificial intelligence 2025-08-13T20:18:05.000000Z
Security and Safety in AI: Adversarial Examples, Bias and Trust w/ Moustapha Cissé - TWiML Talk #108
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) 2024-05-12T05:32:33.000000Z