Was Sie vorher wissen sollten
bevor Sie beginnen
Beginnt 28 June 2026 08:40
Endet 28 June 2026
AI/ML Security - Understanding Jailbreak Prompts and Adversarial Illusions in Large Language Models
RSA Conference
6078 Kurse
47 minutes
Optionales Upgrade verfügbar
Not Specified
Lernen Sie in Ihrem eigenen Tempo
Free Video
Optionales Upgrade verfügbar
Übersicht
Explore jailbreak prompts and adversarial illusions in AI/ML systems through two cutting-edge USENIX security research papers presented by Cornell Tech and Washington University experts.
Fachgebiete
Computer Science
