Older news

Older News

(12/30/24) New paper on arXiv: BridgePure: Revealing the Fragility of Black-box Data Protection.
(12/16/24) I will be an AC for the ICML 2025 Position Paper track.
(12/13/24) Three papers (1, 2, 3) accepted to SaTML 2025.
(12/11/24) A few trips to Italy planned for early 2025: ALT 2025 in Milan, and an ELSA workshop on privacy in Bertinoro.
(12/10/24) A Bias-Accuracy-Privacy Trilemma for Statistical Estimation accepted to the Journal of the American Statistical Association.
(12/3/24) I wrote a survey on connections between various types of robustness, including contamination, heavy-tailed data, and privacy.
(11/15/24) I will be giving talks at two Vector Institute events this month: ICML and ICLR 2024 Conference Highlights, and ML Theory Day.
(11/8/24) I will be a Senior PC member for COLT 2025.
(11/7/24) I will be giving a talk at the 2024 Charles River Privacy Day.
(10/04/24) Private Mean Estimation with Person-Level Differential Privacy accepted to SODA 2025.
(9/30/24) New paper on arXiv: Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data.
(9/16/24) I will be attending the Encore DP workshop in January 2025.
(9/9/24) I will be giving talks at Google's Core Labs seminar on September 25 and NUSAiL AI Horizons seminar on October 3.
(9/2/24) I will be on Ruicheng Xian's PhD committee.
(8/24/24) I will be on the PC of STOC 2025.
(8/20/24) I will be doing an online AMA at the IEEE Computer Society Santa Clara Valley Chapter for IEEE Day.
(7/29/24) I will be a reader for Linfeng Ye's Master's thesis.
(7/25/24) I was quoted in an MIT Technology Review article on copyright traps.
(7/23/24) "Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining" recognized as a Best Paper at ICML 2024.
(7/18/24) "The Discrete Gaussian for Differential Privacy" recognized with the 2024 Caspar Bowden Award for Outstanding Research in Privacy Enhancing Technologies.
(7/1/24) I am a director of the Association for Computational Learning.
(7/1/24) I'm giving the opening keynote at the Toronto Machine Learning Summit.
(6/24/24) New paper on arXiv.
(6/2/24) Two new papers (1, 2) on arXiv.
(5/30/24) I will be program committee co-chair for ALT 2025.
(5/28/24) I gave a talk at the 2024 Canadian Computing Olympiad.
(5/13/24) I am co-organizing a robustness workshop at TTIC from June 12 to 14.
(5/3/24) I will be the social media chair for SaTML 2025.
(5/1/24) Three papers (1, 2, 3) accepted to ICML 2024.
(4/12/24) I will be on the PC of TPDP 2024.
(4/11/24) New paper on arXiv: Disguised Copyright Infringement of Latent Diffusion Models.
(4/2/24) I will be on the PhD thesis committee of Aseem Baranwal.
(4/1/24) I gave a (virtual) guest lecture at Rex Ying's Trustworthy Deep Learning course at Yale.
(3/28/24) I will be an Area Chair for NeurIPS 2024.
(3/7/24) I was quoted in a couple of articles (1, 2) on protections for artists against ML model training.
(2/23/24) I will be giving a talk at NYU Courant on March 25.
(2/8/24) One paper accepted to SaTML 2024.
(2/1/24) I will be giving a talk at Yale CS on February 20.
(1/30/24) I will be a reviewer for ICML 2024 Workshops.
(1/29/24) I will be giving a talk at UCSD Data Science on February 13.
(1/23/24) I will be giving a talk at Cornell ORIE on March 5.
(1/17/24) My URA Matthew Yang was recognized as a Finalist for the CRA Outstanding Undergraduate Researcher Award.
(1/11/24) I was quoted in an Axios Science newsletter on machine unlearning.
(1/8/24) Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment accepted to Harvard Data Science Review.
(1/7/24) Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy accepted to Statistica Sinica.
(1/2/24) Differentially Private Fine-tuning of Language Models accepted to the Journal of Privacy and Confidentiality.
(12/14/23) One paper accepted to ALT 2024.
(12/1/23) I am now a Senior Member of the IEEE.
(11/25/23) I will be a reviewer for the 37th Canadian Artificial Intelligence Conference.
(11/13/23) New paper on arXiv: Report of the 1st Workshop on Generative AI and Law.
(11/3/23) I was quoted in this NPR All Things Considered episode regarding tools to prevent scraping of data for AI systems.
(10/23/23) I am on the steering committee of the TPDP workshop.
(10/23/23) I am now on the executive committee of the Learning Theory Alliance.
(10/23/23) I was quoted in this MIT Tech Review article about data poisoning defenses against generative AI.
(10/20/23) It was a lot of fun being the macebearer for Waterloo Math convocation.
(9/26/23) I will be on the COLT 2024 senior program committee.
(9/21/23) Two posters (1, 2) and one spotlight (1) accepted to NeurIPS 2023.
(9/12/23) This term I'll be in Boston for TPDP 2023, Rochester for EaGL, New York for a robust statistics and privacy workshop, Guelph to give a talk at their CARE-AI seminar series, and at Vector's Distinguished Lecture series (virtually).
(8/28/23) Private GANs, Revisited accepted to TMLR, with a Survey Certification.
(8/15/23) I will be on the program committee of ICBINB 2023 and Regulatable ML @ NeurIPS 2023.
(8/13/23) One paper posted to arXiv: Private Distribution Learning with Public Data: The View from Sample Compression.
(8/11/23) Seven papers to be presented at TPDP 2023.
(8/3/23) One paper accepted to TMLR.
(7/26/23) I was on a panel on social impacts of AI at the ICML 2023 Black in AI social.
(7/20/23) I will be a reader of Abdulrahman Diaa's Master's thesis.
(7/13/23) I am the early-career winner of the 2023 Math Golden Jubilee Research Excellence Award.
(7/11/23) I am now an Editor-in-Chief of TMLR.
(7/4/23) I am organizing and presenting at a Vector workshop on ML Security and Privacy.
(5/16/23) I will be an ethics reviewer for NeurIPS 2023.
(4/27/23) I have been named a Canada CIFAR AI Chair.
(4/24/23) Exploring the Limits of Indiscriminate Data Poisoning Attacks accepted to ICML 2023.
(4/24/23) I will be part of TMLR's first Outstanding Paper Committee.
(4/24/23) I'll be on a panel about disinformation, presenting at a Vector Faculty Research Meeting, and participating in Amii's Upper Bound AI conference.
(04/17/23) Survey paper posted to arXiv: Challenges towards the Next Frontier in Privacy.
(04/12/23) I was quoted in a CBC article about licence plate scanners.
(03/30/23) A bit of upcoming academic travel: event with Health and Statistics Canada in Ottawa in May, teaching a summer school in Bangalore in June, at a Generative AI and Law workshop at ICML in Honolulu in July, BIRS workshop in Kelowna in July, and at JSM 2023 in Toronto in August.
(03/24/23) I talked with the Waterloo Computer Science Club about my research as part of their Prof Talk series. It was a lot of fun!
(03/13/23) I am now a faculty member at the Vector Institute. My role as an Assistant Professor at the University of Waterloo is unchanged.
(03/07/23) New paper on arXiv: Exploring the Limits of Indiscriminate Data Poisoning Attacks.
(03/07/23) I will be a reader of Niki Hasrati's Master's thesis.
(03/02/23) New paper on arXiv: Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance.
(02/28/23) I will be an AC for NeurIPS 2023.
(02/18/23) I will be the Social Media Chair for SaTML 2024.
(02/16/23) Mahbod Majid wins a Waterloo Faculty of Mathematics Graduate Research Excellence Award for the paper "Effcient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism."
(02/13/23) I was recognized as a notable reviewer for SaTML 2023.
(02/06/23) New paper on arXiv: Private GANs, Revisited.
(02/06/23) I'm reviewing for ICML 2023 workshops.
(02/05/23) Robustness Implies Privacy in Statistical Estimation accepted to STOC 2023.
(01/31/23) New paper on arXiv: A Bias-Variance-Privacy Trilemma for Statistical Estimation.