243 citations · 261 across the 5 of their papers we have counts for
5 papers
DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking
Abhishek Chakraborty, Daniel Xing, Yuntao Liu +1
The functionality of a deep learning (DL) model can be stolen via model extraction where an attacker obtains a surrogate model by utilizing the responses from a prediction API of t…
In-situ Stochastic Training of MTJ Crossbar based Neural Networks
Ankit Mondal, Ankur Srivastava
Owing to high device density, scalability and non-volatility, Magnetic Tunnel Junction-based crossbars have garnered significant interest for implementing the weights of an artific…
Data Driven Optimizations for MTJ based Stochastic Computing
Ankit Mondal, Ankur Srivastava
Stochastic computing, a form of computation with probabilities, presents an alternative to conventional arithmetic units. Magnetic Tunnel Junctions (MTJs), which exhibit probabilis…
Neural Trojans
Yuntao Liu, Yang Xie, Ankur Srivastava
While neural networks demonstrate stronger capabilities in pattern recognition nowadays, they are also becoming larger and deeper. As a result, the effort needed to train a network…
Power Optimizations in MTJ-based Neural Networks through Stochastic Computing
Ankit Mondal, Ankur Srivastava
Artificial Neural Networks (ANNs) have found widespread applications in tasks such as pattern recognition and image classification. However, hardware implementations of ANNs using…