5 papers
Privacy in Deep Learning: A Survey
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma +3
The ever-growing advances of deep learning in many areas including vision, recommendation systems, natural language processing, etc., have led to the adoption of Deep Neural Networ…
Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali +3
When receiving machine learning services from the cloud, the provider does not need to receive all features; in fact, only a subset of the features are necessary for the target pre…
Packet Chasing: Spying on Network Packets over a Cache Side-Channel
Mohammadkazem Taram, Ashish Venkat, Dean Tullsen
This paper presents Packet Chasing, an attack on the network that does not require access to the network, and works regardless of the privilege level of the process receiving the p…
Shredder: Learning Noise Distributions to Protect Inference Privacy
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani +2
A wide variety of deep neural applications increasingly rely on the cloud to perform their compute-heavy inference. This common practice requires sending private and privileged dat…
3DCAM: A Low Overhead Crosstalk Avoidance Mechanism for TSV-Based 3D ICs
Reza Mirosanlou, Mohammadkazem Taram, Zahra Shirmohammadi +1
Three Dimensional Integrated Circuits (3D IC) offer lower power consumption, higher performance, higher bandwidth, and scalability over the conventional two dimensional ICs. Throug…