Defend Your AI: Mastering Detection and Prevention of Adversarial Attacks
No ratings
Presented at RSAC 2025 by
Adversarial attacks exploit vulnerabilities in large language models (LLMs), including bias manipulation, jailbreaks, prompt injection, and PII leakage. This session will introduce two frameworks: one for automatic jailbreaking and another for detecting and preventing attacks. Learn actionable strategies to secure AI models and protect sensitive data from evolving threats.