| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 27 Aug 2025 17:00:51 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"68af39c3-6bef"
expires: Tue, 30 Dec 2025 11:07:50 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: B386:36A0B4:9FCB12:B36E4D:6953B02E
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 10:57:50 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210073-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767092270.186076,VS0,VE225
vary: Accept-Encoding
x-fastly-request-id: 9a8bcffefb2cacb81483298bf55470893a099b0d
content-length: 9079
Rouzbeh Behnia
About Me
I am an assistant professor at the School of Information Systems and Management (SISM) at the University of South Florida. I received my Ph.D. in Computer Science from the University of South Florida.
My research focuses on different aspects of cybersecurity and applied cryptography. I am particularly interested in addressing privacy challenges in AI systems, developing post-quantum cryptographic solutions, and enhancing authentication protocols to ensure computation and communication integrity.
Interests
- Secure and Trustworthy AI
- Security with AI
- Applied Crytography and Post-Quantum Security
📣 NEWS
- Aug. 2025: Our paper on zero-knowledge AI inference with high precision was accepted in ACM CCS 2025
- May. 2025: Our paper on dropout-resilient secure aggregation for federated learning in 5G networks was accpeted in ACM WiSec 2025
- May. 2025: Our paper on post-quantum private federated learning was accpeted in IEEE TDSC
- May. 2025: Our paper on interactive framework for privacy-preserving FL won the BEST PAPER AWARD in IEEE S&P Workshops
- Mar. 2025: Our paper on interactive framework for privacy-preserving FL was accepted to IEEE S&P Workshops
- Oct. 2024: Our attack paper on MicroSecAgg (PoPETS 2024) was accepted to ICDM MLC Workshop
- Sep. 2024: Our paper on fixed-size mini batches for Rényi differential privacy was accepted to NeurIPS 2024
- Aug. 2024: Our paper on secure aggregation for federated deep learning was accepted to ACSAC 2024
- Apr. 2024: Our paper on multi-user searchable encryption was accepted to USENIX 2024
Recent Publications
For a complete list of publications, please visit my Google Scholar
Jeremiah Birrell, Reza Ebrahimi, Rouzbeh Behnia, Jason Pacheco
(2024).
Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement.
Accepted to NeurIPS 2024.
Rouzbeh Behnia, Arman Riasi, Mohammadreza Ebrahimi, Sherman S. M. Chow, Balaji Padmanabhan, Thang Hoang
(2024).
Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning.
Accepted to ACSAC 2024.
Tung Le, Rouzbeh Behnia, Jorge Guajardo, Thang Hoang
(2024).
MUSES: Efficient Multi-User Searchable Encrypted Database.
33rd USENIX Security Symposium (USENIX Security 24).
Teaching
Fall 2024
- ISM 4263/6930 Cloud Solution Architecture