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
Dive into a comprehensive conference talk exploring AI Red Teaming for Large Language Models (LLMs), tracing its evolution from 2014 to the present day and examining future prospects. Learn about the origins of AI Red Teaming in computer vision security risk identification and its transition to addressing challenges posed by advanced LLMs like ChatGPT. Examine current security risks including prompt leakage, prompt injection, jailbreaks, poisoning, and logic manipulation attacks. Understand the growing importance of AI Red Teaming skills in business applications and the multidisciplinary expertise required, encompassing computer hacking, AI, social engineering, psychology, neuroscience, mathematics, and logic. Gain insights from industry experts Adarsh Nair, Mohit Joshi, Casey Ellis, and Tom Brennan on the critical role of AI Red Teaming in safeguarding LLMs and shaping the future of cybersecurity.
