157 citations · 253 across the 9 of their papers we have counts for
11 papers
I see what you hear: a vision-inspired method to localize words
Mohammad Samragh, Arnav Kundu, Ting-Yao Hu +5
This paper explores the possibility of using visual object detection techniques for word localization in speech data. Object detection has been thoroughly studied in the contempora…
Trojan Signatures in DNN Weights
Greg Fields, Mohammad Samragh, Mojan Javaheripi +2
Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model…
Unsupervised Information Obfuscation for Split Inference of Neural Networks
Mohammad Samragh, Hossein Hosseini, Aleksei Triastcyn +3
Splitting network computations between the edge device and a server enables low edge-compute inference of neural networks but might expose sensitive information about the test quer…
CLEANN: Accelerated Trojan Shield for Embedded Neural Networks
Mojan Javaheripi, Mohammad Samragh, Gregory Fields +2
We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications. A Trojan attack works by injecting…
GeneCAI: Genetic Evolution for Acquiring Compact AI
Mojan Javaheripi, Mohammad Samragh, Tara Javidi +1
In the contemporary big data realm, Deep Neural Networks (DNNs) are evolving towards more complex architectures to achieve higher inference accuracy. Model compression techniques c…
ASCAI: Adaptive Sampling for acquiring Compact AI
Mojan Javaheripi, Mohammad Samragh, Tara Javidi +1
This paper introduces ASCAI, a novel adaptive sampling methodology that can learn how to effectively compress Deep Neural Networks (DNNs) for accelerated inference on resource-cons…