This lecture was delivered via slides. A link is available on Canvas and pdfs are here

Further reading

• Extracting Training Data from Large Language Models. Nicholas Carlini, Florian Tramèr, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom B. Brown, D. Song, Ú. Erlingsson, Alina Oprea, Colin Raffel. USENIX Security Symposium 2020.