152 citations · 262 across the 7 of their papers we have counts for
7 papers
DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning
Mohammad Hossein Samavatian, Saikat Majumdar, Kristin Barber +1
DNNs are known to be vulnerable to so-called adversarial attacks that manipulate inputs to cause incorrect results that can be beneficial to an attacker or damaging to the victim.…
Using Undervolting as an On-Device Defense Against Adversarial Machine Learning Attacks
Saikat Majumdar, Mohammad Hossein Samavatian, Kristin Barber +1
Deep neural network (DNN) classifiers are powerful tools that drive a broad spectrum of important applications, from image recognition to autonomous vehicles. Unfortunately, DNNs a…
HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks
Mohammad Hossein Samavatian, Saikat Majumdar, Kristin Barber +1
Deep Neural Networks (DNNs) are employed in an increasing number of applications, some of which are safety critical. Unfortunately, DNNs are known to be vulnerable to so-called adv…
Accident Risk Prediction based on Heterogeneous Sparse Data: New Dataset and Insights
Sobhan Moosavi, Mohammad Hossein Samavatian, Srinivasan Parthasarathy +2
Reducing traffic accidents is an important public safety challenge, therefore, accident analysis and prediction has been a topic of much research over the past few decades. Using s…
A Countrywide Traffic Accident Dataset
Sobhan Moosavi, Mohammad Hossein Samavatian, Srinivasan Parthasarathy +1
Reducing traffic accidents is an important public safety challenge. However, the majority of studies on traffic accident analysis and prediction have used small-scale datasets with…
Short and Long-term Pattern Discovery Over Large-Scale Geo-Spatiotemporal Data
Sobhan Moosavi, Mohammad Hossein Samavatian, Arnab Nandi +2
Pattern discovery in geo-spatiotemporal data (such as traffic and weather data) is about finding patterns of collocation, co-occurrence, cascading, or cause and effect between geos…
RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory
Mohammad Hossein Samavatian, Anys Bacha, Li Zhou +1
Recurrent Neural Networks (RNNs) are an important class of neural networks designed to retain and incorporate context into current decisions. RNNs are particularly well suited for…