Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to protect large language models from adversarial attacks through this 48-minute conference talk from RSA Conference featuring Innovation Engineer Shai Dvash and Principal Security Researcher Eran Shimony from CyberArk. Explore the vulnerabilities that attackers exploit in LLMs, including bias manipulation, jailbreaks, prompt injection, and personally identifiable information (PII) leakage. Discover two comprehensive frameworks: an automatic jailbreaking framework that demonstrates attack methodologies, and a detection and prevention framework designed to counter these threats. Gain actionable strategies for securing AI models and protecting sensitive data from evolving adversarial threats in the rapidly changing landscape of artificial intelligence security.
