Scholar
Milad Nasr
Google Scholar ID: k6-nvDAAAAAJ
OpenAI
Citations & Impact
Citations
18,601
H-index
29
i10-index
43
Publications
20
Co-authors
19
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - Privacy Auditing with One (1) Training Run (NeurIPS, 2023)
- - Tight Auditing of Differentially Private Machine Learning (USENIX Security, 2023)
- - Extracting Training Data from Diffusion Models (USENIX Security, 2023)
- - Membership inference attacks from first principles (IEEE Symposium on Security and Privacy (SP) 2022)
- - Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning (IEEE Symposium on Security and Privacy (SP) 2021)
Research Experience
- Research Scientist at Google DeepMind, focusing on machine learning privacy and security.
Education
- PhD from the University of Massachusetts Amherst in 2022, where he worked on designing censorship circumvention technologies and also studying machine learning privacy.
Background
- Research interests: understanding the security and privacy issues of machine learning systems; developing techniques to mitigate these risks; circumventing internet censorship.
