Readings for Week 6

Updates

Reading for Thursday, 12 February (repeated from Readings for Week 4):

  • Milad Nasr, Javier Rando, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Florian Tramèr, and Katherine Lee. Scalable extraction of training data from aligned, production language models. In International Conference on Learning Representations (ICLR) 2025. ICLR Web Link. (You can also see the review discussion: ICLR Forum)

One of the authors of this paper, Matthew Jagielski (now at Anthropic), will visit UVA on Friday, 13 February and give a Distinguished Talk at 11:00am Friday, 13 February, in Rice 540.

Readings for Next Week

Next week, we’ll focus on how AI tools are changing software development, and what that means both for programmers specifically and for humanity more broadly.

Readings for Tuesday, 17 February

Readings for Thursday, 19 February

  • Jessica Ji, Jenny Jun, Maggie Wu, and Rebecca Gelles. Cybersecurity Risks of AI-Generated Code. CSET Report, November 2024. This is a long report and you are not expected to read the full report, but you should skim it to see what it covers, and pick sections that you think are interesting to read in more details. [Report Webpage] [PDF]

Read at least one of the two posts below: