HackTalk: Juan Felipe Cerón Uribe - Adversarial robustness
Registration
About Event
HackTalk: Juan Felipe Cerón Uribe
Adversarial robustness
Closing-day talk for the Global South AI Safety Hackathon, June 19-21 online. Free and open.
Juan Felipe Cerón Uribe is an AI Alignment Research Engineer at OpenAI in San Francisco, where he works on mitigating existential risks from artificial intelligence. He previously built AI systems at Factored and was a research intern at the Stanford Existential Risks Initiative.
His talk is an overview of adversarial robustness.
Format: ~15-25 min talk + 10-15 min Q&A. Online (Zoom), livestreamed. Recording subject to review.
Part of the Global South AI Safety Hackathon, June 19-21, online with in-person hubs across Latin America, Africa, and Asia. Organized by Apart Research.