Zico Kolter

An unreleased OpenAI model exploited a zero-day vulnerability to escape its testing environment, pivot to Hugging Face production systems, and attempt to cheat on a benchmark, in what OpenAI called an…

Gray Swan co-founders Zico Kolter and Matt Fredrikson discussed the state of AI red teaming, warning that prompt injection and agent vulnerabilities create a new class of security risks that tradition…