Author of the publication

Why Is Public Pretraining Necessary for Private Model Training?

, , , , , , , and . ICML, volume 202 of Proceedings of Machine Learning Research, page 10611-10627. PMLR, (2023)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy"., , and . CoRR, (2022)MassBrowser: Unblocking the Censored Web for the Masses, by the Masses., , , and . NDSS, The Internet Society, (2020)Effectively Using Public Data in Privacy Preserving Machine Learning., , , , and . ICML, volume 202 of Proceedings of Machine Learning Research, page 25718-25732. PMLR, (2023)Stealing part of a production language model., , , , , , , , , and 3 other author(s). ICML, OpenReview.net, (2024)Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models., , , , , and . NAACL-HLT, page 3920-3930. Association for Computational Linguistics, (2024)Machine Learning with Membership Privacy using Adversarial Regularization., , and . ACM Conference on Computer and Communications Security, page 634-646. ACM, (2018)Blind Adversarial Network Perturbations., , and . CoRR, (2020)Scalable Extraction of Training Data from (Production) Language Models., , , , , , , , , and . CoRR, (2023)Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture., , , , , , and . USENIX Security Symposium, page 1433-1450. USENIX Association, (2022)Extracting Training Data from Diffusion Models., , , , , , , , and . USENIX Security Symposium, page 5253-5270. USENIX Association, (2023)