Syed Mahbub Hafiz
Computer Science · Indiana University
Publications
11
Citations
53
Est. group size
—
Recurring co-author estimate
Active years
13
Publishing since 2012
Syed Mahbub Hafiz works in computer security and privacy, developing methods that let people query databases without revealing what they are searching for (private information retrieval) and studying the security of machine learning systems. Recent work spans protecting queries to untrusted databases, secure trading of machine learning models, and attacks that can steal or fingerprint neural network models through hardware side channels.
Publication activity has been steady but modest over the last decade, averaging about one paper per year.
Generated by claude-opus-4-8 from public bibliographic data · Jul 11, 2026
- Private Aggregate Queries to Untrusted Databases
2024
- Private Aggregate Queries to Untrusted Databases
arXiv (Cornell University) · 2024
- Benchmarking Adversarial Robustness of Compressed Deep Learning Models
arXiv (Cornell University) · 2023
- DNN Model Architecture Fingerprinting Attack on CPU-GPU Edge Devices
2022
- Stealthy Inference Attack on DNN via Cache-based Side-Channel Attacks
2022 Design, Automation & Test in Europe Conference & Exhibition (DATE) · 2022
- Gimme That Model!: A Trusted ML Model Trading Protocol
2021
- Gimme That Model!: A Trusted ML Model Trading Protocol
arXiv (Cornell University) · 2020
- A Bit More Than a Bit Is More Than a Bit Better
Proceedings on Privacy Enhancing Technologies · 2019
- Querying for Queries
2017
- Querying for Queries: Indexes of Queries for Efficient and Expressive IT-PIR.
IACR Cryptology ePrint Archive · 2017
- arXiv (Cornell University)×3
- Proceedings on Privacy Enhancing Technologies×1
- 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)×1
- IACR Cryptology ePrint Archive×1
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 11, 2026.
Claim or correct this profile