SaTML 2023 - Carlini & Jagielski - Improving train data extraction attacks on large language models
▶SaTML 2023 - Carlini & Jagielski - Improving train data extraction attacks on large language models — a 2023 IEEE SaTML 2023 - 1st Conference on Secure and Trustworthy Machine Learning security conference talk on ai-ml, privacy (58:03 min). Watch the full video, indexed free on the Breach Arc Archive.
▶ Watch video on YouTube