Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
This conference talk explores the security and privacy challenges of integrating Large Language Models (LLMs) into applications. Discover how LLMs accessing databases and intelligent agents performing online purchases create both opportunities and significant risks. Learn about critical vulnerabilities including prompt injection, key leakage, misuse of private customer data for model training, and relevant legal restrictions. Understand how general security issues in your systems can impact LLM behavior and outcomes. Gain a comprehensive overview of vulnerabilities to avoid, strategies for data privacy compliance, and best practices for building secure LLM-powered applications in this 49-minute Devoxx presentation by Brian Vermeer.
