Scholar
Sahra Ghalebikesabi
Google Scholar ID: fCmDlHYAAAAJ
Research Scientist at Google DeepMind
LLM Reasoning
Privacy
Alignment
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
746
H-index
10
i10-index
10
Publications
20
Co-authors
12
list available
Contact
Email
sghal@google.com
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
1 items
Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models
2025
Cited
0
Resume (English only)
Academic Achievements
- Publications: See the 'Publications' section on her personal website
- Workshops Organized: MINT workshop at NeurIPS 2024; 'I can’t believe it’s not better - workshop' at NeurIPS 2022 and 2023
- Conference Roles: Communications Chair at NeurIPS 2022 and 2023; Publications Chair at AISTATS 2022
Research Experience
- Interned with the Health Intelligence team at Microsoft Research Cambridge on robust representation learning
- Interned in the Robust and Verified AI group at Google DeepMind during doctoral studies
Education
- Degree: PhD
- University: University of Oxford
- Supervisor: Chris Holmes
- Field: Statistical Machine Learning
- Time: Not explicitly stated
- Funding: Microsoft Research PhD Fellowship, EPSRC, Novartis
Background
- Research Interests: Language model inference and user privacy
- Position: Research Scientist at Google DeepMind
Miscellany
- Social Media: Twitter, GitHub, Google Scholar
Co-authors
12 total
Chris Holmes
Unknown affiliation
Borja Balle
DeepMind
Eugene Bagdasarian
UMass Amherst, Google
Ren Yi
Google
Leonard Berrada
Research Scientist, DeepMind
Jamie Hayes
Google DeepMind
Luke J. Kelly
University College Cork
Jack Jewson
Department of Econometrics and Business Statistics, Monash University
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up