| CARVIEW |
Select Language
HTTP/2 200
date: Tue, 30 Dec 2025 00:22:44 GMT
content-type: text/html
server: cloudflare
last-modified: Sat, 10 Feb 2024 00:26:11 GMT
nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800}
report-to: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=Xe3AMa91IF5obez%2BK91hCe24ldbQahLCH7cB0cOuB4NL6LZSITH1gXNccwb%2FRTDZjMzyw%2F82t7cZ8ytHGKWwA732gbQK3JvvsA%3D%3D"}]}
vary: accept-encoding
cf-cache-status: DYNAMIC
content-encoding: gzip
cf-ray: 9b5d626e0f178374-BOM
alt-svc: h3=":443"; ma=86400
Milad Nasr
I am a researcher at Google DeepMind, where I work on machine learning privacy and security. My research interests include understanding the security and privacy issues of machine learning systems and developing techniques to mitigate these risks. I am also interested in circumventing internet censorship. I received my PhD from the University of Massachusetts Amherst in 2022, where I worked on designing censorship circumvention technologies and also studying machine learning privacy.
Selected Recent works
2023
- Privacy Auditing with One (1) Training Run
Thomas Steinke, Milad Nasr and Matthew Jagielski
NeurIPS, 2023 (Outstanding Paper). - Tight Auditing of Differentially Private Machine Learning
Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis
USENIX Security, 2023 (Distinguished Paper). - Extracting Training Data from Diffusion Models
Nicholas Carlini*, Jamie Hayes*, Milad Nasr*, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric Wallace
USENIX Security, 2023.
2022
- Membership inference attacks from first principles
Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, Florian Tramer
IEEE Symposium on Security and Privacy (SP) 2022.
2021
- Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning
Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini
IEEE Symposium on Security and Privacy (SP) 2021.