11 papers
Efficient and Privacy-Preserving Binary Dot Product via Multi-Party Computation
Fatemeh Jafarian Dehkordi, Elahe Vedadi, Alireza Feizbakhsh +2
Striking a balance between protecting data privacy and enabling collaborative computation is a critical challenge for distributed machine learning. While privacy-preserving techniq…
Privacy-Preserving Hierarchical Model-Distributed Inference
Fatemeh Jafarian Dehkordi, Yasaman Keshtkarjahromi, Hulya Seferoglu
This paper focuses on designing a privacy-preserving Machine Learning (ML) inference protocol for a hierarchical setup, where clients own/generate data, model owners (cloud servers…
Efficient Coded Multi-Party Computation at Edge Networks
Elahe Vedadi, Yasaman Keshtkarjahromi, Hulya Seferoglu
Multi-party computation (MPC) is promising for designing privacy-preserving machine learning algorithms at edge networks. An emerging approach is coded-MPC (CMPC), which advocates…
Adaptive Gap Entangled Polynomial Coding for Multi-Party Computation at the Edge
Elahe Vedadi, Yasaman Keshtkarjahromi, Hulya Seferoglu
Multi-party computation (MPC) is promising for designing privacy-preserving machine learning algorithms at edge networks. An emerging approach is coded-MPC (CMPC), which advocates…
PolyDot Coded Privacy Preserving Multi-Party Computation at the Edge
Elahe Vedadi, Yasaman Keshtkarjahromi, Hulya Seferoglu
We investigate the problem of privacy preserving distributed matrix multiplication in edge networks using multi-party computation (MPC). Coded multi-party computation (CMPC) is an…
Robust and Computationally-Efficient Anomaly Detection using Powers-of-Two Networks
Usama Muneeb, Erdem Koyuncu, Yasaman Keshtkarjahromi +3
Robust and computationally efficient anomaly detection in videos is a problem in video surveillance systems. We propose a technique to increase robustness and reduce computational…