Hello! I'm an Applied Scientist at Microsoft, working on AI + Security research.
I received my PhD in Electrical Engineering from Stanford University, where I was advised by Ayfer Özgür and supported in part by a Cisco Systems Stanford Graduate Fellowship (SGF) (2018-2022) and a Stanford Institute for Human-Centered Artificial Intelligence (HAI) Graduate Fellowship (2022-2023). Before that, I received my BSE in Electrical Engineering from Princeton University, with certificates (minors) in Applications of Computing and Robotics & Intelligent Systems.
My PhD research applied the tools and principles of information theory to different statistical inference and machine learning problems. Specifically, I worked on privacy-preserving & communication-efficient federated analytics, and group testing in the presence of correlations. I also completed two internships at Microsoft (2021 & 2022), where I developed Explainable AI tools for security & compliance applications.
Contact
Email: surinahn [at] microsoft [dot] com
Recent Publications
Please see my Google Scholar for a more complete list.
Journals
Adaptive Group Testing on Networks with Community Structure: The Stochastic Block Model
Surin Ahn, Wei-Ning Chen, and Ayfer Özgür
IEEE Transactions on Information Theory, 2023
Global Multiclass Classification and Dataset Construction via Heterogeneous Local Experts
Surin Ahn, Ayfer Özgür, and Mert Pilanci
IEEE Journal on Selected Areas in Information Theory (JSAIT): Special Issue on Estimation and Inference, 2020
Conferences
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Huiqiang Jiang, Yucheng Li, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu
Conference on Neural Information Processing Systems (NeurIPS), 2024 - Spotlight
International Conference on Machine Learning (ICML) Workshop on Efficient Systems for Foundation Models (ES-FoMo), 2024
Noisy Adaptive Group Testing for Community-Oriented Models
Surin Ahn, Wei-Ning Chen, and Ayfer Özgür
IEEE International Symposium on Information Theory (ISIT), 2023
Uncertainty Quantification for Local Model Explanations Without Model Access
Surin Ahn, Justin Grana, Yafet Tamene, and Kristian Holsheimer
Presented in part at the Microsoft Machine Learning, AI & Data Science Conference (MLADS), 2022
Estimating Sparse Distributions Under Joint Communication and Privacy Constraints
Surin Ahn, Wei-Ning Chen, and Ayfer Özgür
IEEE International Symposium on Information Theory (ISIT), 2022
Adaptive Group Testing on Networks with Community Structure
Surin Ahn, Wei-Ning Chen, and Ayfer Özgür
IEEE International Symposium on Information Theory (ISIT), 2021
A Group Testing Approach to Random Access for Short-Packet Communication
Huseyin A. Inan, Surin Ahn, Peter Kairouz, and Ayfer Özgür
IEEE International Symposium on Information Theory (ISIT), 2019
Teaching & Mentoring
Stanford University
ENGR 76: Information Science and Engineering (Spring 2023): Head Course Assistant
ENGR 76: Information Science and Engineering (Spring 2022): Course Assistant
STEM to SHTEM Summer Research Program (Summer 2020): Mentor
Princeton University
ELE 302: Building Real Systems (Spring 2018): Teaching Assistant
ELE 206 / COS 306: Contemporary Logic Design (Fall 2016): Teaching Assistant
Professional Activities
I have served as a reviewer for the following journals / conferences / workshops:
IEEE Transactions on Information Theory
IEEE Transactions on Signal Processing
IEEE Open Journal of Signal Processing
IEEE Transactions on Information Forensics & Security
IEEE International Symposium on Information Theory (ISIT): 2021-2023
ICML Workshop on Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning (ICML ITR3): 2021
IEEE Information Theory Workshop (ITW): 2020