129 citations · 740 across the 61 of their papers we have counts for
7 papers · 1 filter
FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning
Faiq Khalid, Muhammmad Abdullah Hanif, Semeen Rehman +2
Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior…
CapsAcc: An Efficient Hardware Accelerator for CapsuleNets with Data Reuse
Alberto Marchisio, Muhammad Abdullah Hanif, Muhammad Shafique
Deep Neural Networks (DNNs) have been widely deployed for many Machine Learning applications. Recently, CapsuleNets have overtaken traditional DNNs, because of their improved gener…
SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters
Hassan Ali, Faiq Khalid, Hammad Tariq +4
In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allo…
QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks
Faiq Khalid, Hassan Ali, Hammad Tariq +4
Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs). In this paper, we propose two quan…
TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks
Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman +2
Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference o…
MPNA: A Massively-Parallel Neural Array Accelerator with Dataflow Optimization for Convolutional Neural Networks
Muhammad Abdullah Hanif, Rachmad Vidya Wicaksana Putra, Muhammad Tanvir +3
The state-of-the-art accelerators for Convolutional Neural Networks (CNNs) typically focus on accelerating only the convolutional layers, but do not prioritize the fully-connected…
A Methodology for Automatic Selection of Activation Functions to Design Hybrid Deep Neural Networks
Alberto Marchisio, Muhammad Abdullah Hanif, Semeen Rehman +2
Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Expon…