Nicolas Papernot
@nicolaspapernot.bsky.social
Security and Privacy of Machine Learning at UofT, Vector Institute, and Google 🇨🇦🇫🇷🇪🇺 Co-Director of Canadian AI Safety Institute (CAISI) Research Program at CIFAR. Opinions mine
Félicitations pour cette reconnaissance, Gaël !
October 11, 2025 at 2:09 AM
Félicitations pour cette reconnaissance, Gaël !
Congratulations to my fellow awardees Rose Yu (UCSD) and Lerrel Pinto (NYU)!
I enjoyed learning about the work of Yoshua, Rose, and Lerrel at the Samsung AI Forum earlier this week.
news.samsung.com/global/samsu...
I enjoyed learning about the work of Yoshua, Rose, and Lerrel at the Samsung AI Forum earlier this week.
news.samsung.com/global/samsu...
September 22, 2025 at 12:35 AM
Congratulations to my fellow awardees Rose Yu (UCSD) and Lerrel Pinto (NYU)!
I enjoyed learning about the work of Yoshua, Rose, and Lerrel at the Samsung AI Forum earlier this week.
news.samsung.com/global/samsu...
I enjoyed learning about the work of Yoshua, Rose, and Lerrel at the Samsung AI Forum earlier this week.
news.samsung.com/global/samsu...
Congratulations Maksym, this is a great place to start your research group! Looking forward to following your work
August 6, 2025 at 7:24 PM
Congratulations Maksym, this is a great place to start your research group! Looking forward to following your work
Reposted by Nicolas Papernot
📄 Selective Prediction Via Training Dynamics
Paper ➡️ arxiv.org/abs/2205.13532
Workshop ➡️ 3rd Workshop on High-dimensional Learning Dynamics (HiLD)
Poster ➡️ West Meeting Room 118-120 on Sat 19 Jul 10:15 a.m. — 11:15 a.m. & 4:45 p.m. — 5:30 p.m.
Paper ➡️ arxiv.org/abs/2205.13532
Workshop ➡️ 3rd Workshop on High-dimensional Learning Dynamics (HiLD)
Poster ➡️ West Meeting Room 118-120 on Sat 19 Jul 10:15 a.m. — 11:15 a.m. & 4:45 p.m. — 5:30 p.m.
July 11, 2025 at 8:04 PM
📄 Selective Prediction Via Training Dynamics
Paper ➡️ arxiv.org/abs/2205.13532
Workshop ➡️ 3rd Workshop on High-dimensional Learning Dynamics (HiLD)
Poster ➡️ West Meeting Room 118-120 on Sat 19 Jul 10:15 a.m. — 11:15 a.m. & 4:45 p.m. — 5:30 p.m.
Paper ➡️ arxiv.org/abs/2205.13532
Workshop ➡️ 3rd Workshop on High-dimensional Learning Dynamics (HiLD)
Poster ➡️ West Meeting Room 118-120 on Sat 19 Jul 10:15 a.m. — 11:15 a.m. & 4:45 p.m. — 5:30 p.m.
Reposted by Nicolas Papernot
📄 Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings (✨ oral paper ✨)
Paper ➡️ arxiv.org/abs/2505.22356
Poster ➡️ E-504 on Thu 17 Jul 4:30 p.m. — 7 p.m.
Oral Presentation ➡️ West Ballroom C on Thu 17 Jul 4:15 p.m. — 4:30 p.m.
Paper ➡️ arxiv.org/abs/2505.22356
Poster ➡️ E-504 on Thu 17 Jul 4:30 p.m. — 7 p.m.
Oral Presentation ➡️ West Ballroom C on Thu 17 Jul 4:15 p.m. — 4:30 p.m.
July 11, 2025 at 8:04 PM
📄 Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings (✨ oral paper ✨)
Paper ➡️ arxiv.org/abs/2505.22356
Poster ➡️ E-504 on Thu 17 Jul 4:30 p.m. — 7 p.m.
Oral Presentation ➡️ West Ballroom C on Thu 17 Jul 4:15 p.m. — 4:30 p.m.
Paper ➡️ arxiv.org/abs/2505.22356
Poster ➡️ E-504 on Thu 17 Jul 4:30 p.m. — 7 p.m.
Oral Presentation ➡️ West Ballroom C on Thu 17 Jul 4:15 p.m. — 4:30 p.m.
Reposted by Nicolas Papernot
📄 Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
TL;DR ➡️ We show that a model owner can artificially introduce uncertainty and provide a detection mechanism.
Paper ➡️ arxiv.org/abs/2505.23968
Poster ➡️ E-1002 on Wed 16 Jul 11 a.m. — 1:30 p.m.
TL;DR ➡️ We show that a model owner can artificially introduce uncertainty and provide a detection mechanism.
Paper ➡️ arxiv.org/abs/2505.23968
Poster ➡️ E-1002 on Wed 16 Jul 11 a.m. — 1:30 p.m.
July 11, 2025 at 8:04 PM
📄 Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
TL;DR ➡️ We show that a model owner can artificially introduce uncertainty and provide a detection mechanism.
Paper ➡️ arxiv.org/abs/2505.23968
Poster ➡️ E-1002 on Wed 16 Jul 11 a.m. — 1:30 p.m.
TL;DR ➡️ We show that a model owner can artificially introduce uncertainty and provide a detection mechanism.
Paper ➡️ arxiv.org/abs/2505.23968
Poster ➡️ E-1002 on Wed 16 Jul 11 a.m. — 1:30 p.m.
Félicitations Yoshua !! C'est plus que mérité.
June 12, 2025 at 3:58 PM
Félicitations Yoshua !! C'est plus que mérité.
Reposted by Nicolas Papernot
As part of the theme Societal Aspects of Securing the Digital Society, I will be hiring PhD students and postdocs at #MPI-SP, focusing in particular on the computational and sociotechnical aspects of technology regulations and the governance of emerging tech. Get in touch if interested.
May 23, 2025 at 2:12 PM
As part of the theme Societal Aspects of Securing the Digital Society, I will be hiring PhD students and postdocs at #MPI-SP, focusing in particular on the computational and sociotechnical aspects of technology regulations and the governance of emerging tech. Get in touch if interested.
Congrats on what looks like an amazing event, Konrad!
April 10, 2025 at 4:11 PM
Congrats on what looks like an amazing event, Konrad!
Very exciting! Congratulations to the organizing team on what looks like an amazing event!
April 9, 2025 at 2:16 PM
Very exciting! Congratulations to the organizing team on what looks like an amazing event!
I think the talk is being streamed but only internally within the MPI. I'm not sure if you still have access from your time there?
March 8, 2025 at 4:06 PM
I think the talk is being streamed but only internally within the MPI. I'm not sure if you still have access from your time there?