School of Informatics · University of Edinburgh
Sahel Torkamani
School of Informatics · University of Edinburgh
I am a Ph.D. student in Computer Science at the University of Edinburgh, advised by Professor Rik Sarkar. My research focuses on Differential Privacy and Theoretical Machine Learning.
I completed my B.Sc. in Applied Mathematics at Sharif University of Technology, working with Professor Javad Ebrahimi on Differential Privacy and Information Theory. I also interned at IST Austria with Professor Marco Mondelli on Channel Coding and Machine Learning.
Research Interests
Selected Honors
Hover over a project to read more.
Potential Privacy Risk in Machine Learning
December 2024 – Ongoing
Advanced estimation of privacy risk of adding a data point to the training set of a machine learning model with standard optimisation methods.
Secure Data Scoring & Selection for ML with Zero-Knowledge Proofs
December 2024 – April 2025
Secure protocols using a small subset of data to assess and price data transactions, based on zero-knowledge proofs of data properties and model inference.
Continual Observation with Differential Privacy
March 2024 – September 2024
A new generalization of the binary tree mechanism using a k-ary number system with negative digits to improve the privacy-accuracy trade-off for counting under continual observation.
Sparse MultiDecoder Recursive Projection Aggregation for Reed-Muller Codes
March 2022 – September 2022
Neural network-based algorithm achieving near-maximum-likelihood performance for RM codes via better projection selection in each sparsified decoder.
Algorithms and Differential Privacy via Graphs
March 2021 – February 2024
Generalized framework for utility-optimal DP mechanisms via graphs, extended to heterogeneous mechanisms and general heterogeneous privacy settings on neighboring datasets.
2024 – 2028
University of Edinburgh
2019 – 2023
Sharif University of Technology
2013 – 2019
National Organization for the Development of Exceptional Talent
December 2025
Attending the Workshop on Principles of Generative Modeling (PriGM) @ EurIPS2025.
OpenReviewClick any photo to explore.
