Congrats to Jimmy Di, recipient of a Vector Scholarship in AI from Vector Institute! Jimmy will be conducting research on privacy and security in machine learning with Cheriton School of Computer Science Professor Gautam Kamath Gautam Kamath this fall. cs.uwaterloo.ca/news/jimmy-di-…

Truly bittersweet news. Consciously glad and hopeful for other places to follow suit, but also discouraged by how long it took to get here. harvard.edu/admissionscase…

Now I realize the real benefits of being in academia. No coding interviews!

Local Chinese grocery store has banned generative AI

🧵New paper: Machine Unlearning Fails to Remove Data Poisoning Attacks, ft Martin Pawelczyk (on Job Market), Jimmy Di, Ayush Sekhari (on Job Market), Seth Neel. Title says it all: current approaches for machine unlearning (MUL) are not effective at removing the effect of data poisoning attacks. 1/n

Can current unlearning methods remove poisoned training data from a trained model? Our new paper shows that unlearning methods are not quite ready, yet. Looking forward to a lot of interesting work ahead in this area.

📢📢 Happy to share that our paper on unlearning evaluations has been accepted to ICLR 2025 🇸🇬 📜: arxiv.org/abs/2406.17216 Thanks to my great co-authors Seth Neel Gautam Kamath Jimmy Di Ayush Sekhari @yiweilu

Super excited to be here at the ICLR Conference held at the Singapore Expo to present our work: Machine Unlearning Fails to Remove Data Poisoning Attacks. Our session will take place on April 25th at 10-12 in Hall 3 Booth #497. If you are interested, please drop by and say hi! pic.x.com/6pDdbqmJfa

Congrats to Dr. Yiwei Lu (Yiwei Lu), who defended his PhD today! Yiwei is a leader in trustworthy AI&ML, and has done breakthrough work on data poisoning attacks. He will be starting as an assistant professor at Université d'Ottawa | University of Ottawa in the fall -- apply to work with him! 💯💯💯

Third time’s a charm! Canadian Blood Services

Big news for AI research in Canada 🧠 Vector Institute just elevated 13 researchers to Faculty Member status, expanding our core research leadership across Ontario. Our faculty community now includes: → 55 Faculty Members → 106 Faculty Affiliates → 960+ researchers across

In TSM I believe. #TSMWIN