Search Results for author: Muhammad Shafique

Found 44 papers, 8 papers with code

Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework

no code implementations20 Sep 2021 Muhammad Shafique, Alberto Marchisio, Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif

Afterward, we discuss how to further improve the performance (latency) and the energy efficiency of Edge AI systems through HW/SW-level optimizations, such as pruning, quantization, and approximation.

Quantization

BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables

no code implementations7 Sep 2021 Bharath Srinivas Prabakaran, Asima Akhtar, Semeen Rehman, Osman Hasan, Muhammad Shafique

We are successful in identifying Pareto-optimal designs, which can reduce the storage overhead of the DNN by ~30MB for a quality loss of less than 0. 5%.

Model Compression

R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors

1 code implementation1 Sep 2021 Alberto Marchisio, Giacomo Pira, Maurizio Martina, Guido Masera, Muhammad Shafique

Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS).

ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories

no code implementations23 Aug 2021 Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique

Since recent works still focus on the fault-modeling and random fault injection in SNNs, the impact of memory faults in SNN hardware architectures on accuracy and the respective fault-mitigation techniques are not thoroughly explored.

Q-SpiNN: A Framework for Quantizing Spiking Neural Networks

no code implementations5 Jul 2021 Rachmad Vidya Wicaksana Putra, Muhammad Shafique

A prominent technique for reducing the memory footprint of Spiking Neural Networks (SNNs) without decreasing the accuracy significantly is quantization.

Quantization

DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networks

1 code implementation1 Jul 2021 Alberto Marchisio, Giacomo Pira, Maurizio Martina, Guido Masera, Muhammad Shafique

Spiking Neural Networks (SNNs), despite being energy-efficient when implemented on neuromorphic hardware and coupled with event-based Dynamic Vision Sensors (DVS), are vulnerable to security threats, such as adversarial attacks, i. e., small perturbations added to the input for inducing a misclassification.

Adversarial Attack

Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

no code implementations26 May 2021 Khadija Shaheen, Muhammad Abdullah Hanif, Osman Hasan, Muhammad Shafique

Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions.

Continual Learning

Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks

no code implementations5 May 2021 Faiq Khalid, Muhammad Abdullah Hanif, Muhammad Shafique

From tiny pacemaker chips to aircraft collision avoidance systems, the state-of-the-art Cyber-Physical Systems (CPS) have increasingly started to rely on Deep Neural Networks (DNNs).

SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments

no code implementations28 Feb 2021 Rachmad Vidya Wicaksana Putra, Muhammad Shafique

Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility, but their complexity still poses a serious research challenge to enable their energy-efficient design for resource-constrained scenarios (like embedded systems, IoT-Edge, etc.).

Continual Learning

SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAM

no code implementations28 Feb 2021 Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique

The key mechanisms of SparkXD are: (1) improving the SNN error tolerance through fault-aware training that considers bit errors from approximate DRAM, (2) analyzing the error tolerance of the improved SNN model to find the maximum tolerable bit error rate (BER) that meets the targeted accuracy constraint, and (3) energy-efficient DRAM data mapping for the resilient SNN model that maps the weights in the appropriate DRAM location to minimize the DRAM access energy.

DNN-Life: An Energy-Efficient Aging Mitigation Framework for Improving the Lifetime of On-Chip Weight Memories in Deep Neural Network Hardware Architectures

no code implementations29 Jan 2021 Muhammad Abdullah Hanif, Muhammad Shafique

We propose DNN-Life, a specialized aging analysis and mitigation framework for DNNs, which jointly exploits hardware- and software-level knowledge to improve the lifetime of a DNN weight memory with reduced energy overhead.

Quantization Hardware Architecture

Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead

no code implementations4 Jan 2021 Muhammad Shafique, Mahum Naseer, Theocharis Theocharides, Christos Kyrkou, Onur Mutlu, Lois Orosa, Jungwook Choi

Machine Learning (ML) techniques have been rapidly adopted by smart Cyber-Physical Systems (CPS) and Internet-of-Things (IoT) due to their powerful decision-making capabilities.

Decision Making

MLComp: A Methodology for Machine Learning-based Performance Estimation and Adaptive Selection of Pareto-Optimal Compiler Optimization Sequences

no code implementations9 Dec 2020 Alessio Colucci, Dávid Juhász, Martin Mosbeck, Alberto Marchisio, Semeen Rehman, Manfred Kreutzer, Guenther Nadbath, Axel Jantsch, Muhammad Shafique

Training of the policy is supported by Machine Learning-based analytical models for quick performance estimation, thereby drastically reducing the time spent for dynamic profiling.

Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters

1 code implementation9 Dec 2020 Rida El-Allami, Alberto Marchisio, Muhammad Shafique, Ihsen Alouani

We thoroughly study SNNs security under different adversarial attacks in the strong white-box setting, with different noise budgets and under variable spiking parameters.

MacLeR: Machine Learning-based Run-Time Hardware Trojan Detection in Resource-Constrained IoT Edge Devices

no code implementations21 Nov 2020 Faiq Khalid, Syed Rafay Hasan, Sara Zia, Osman Hasan, Falah Awwad, Muhammad Shafique

To reduce the overhead of data acquisition, we propose a single power-port current acquisition block using current sensors in time-division multiplexing, which increases accuracy while incurring reduced area overhead.

DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware

no code implementations12 Oct 2020 Alberto Marchisio, Vojtech Mrazek, Muhammad Abdullah Hanif, Muhammad Shafique

We analyze the corresponding on-chip memory requirements and leverage it to propose a novel methodology to explore different scratchpad memory designs and their energy/area trade-offs.

NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks

1 code implementation19 Aug 2020 Alberto Marchisio, Andrea Massa, Vojtech Mrazek, Beatrice Bussolino, Maurizio Martina, Muhammad Shafique

Deep Neural Networks (DNNs) have made significant improvements to reach the desired accuracy to be employed in a wide variety of Machine Learning (ML) applications.

Neural Architecture Search

FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks

no code implementations17 Jul 2020 Rachmad Vidya Wicaksana Putra, Muhammad Shafique

FSpiNN reduces the computational requirements by reducing the number of neuronal operations, the STDP-based synaptic weight updates, and the STDP complexity.

Quantization

NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips

no code implementations16 May 2020 Valerio Venceslai, Alberto Marchisio, Ihsen Alouani, Maurizio Martina, Muhammad Shafique

Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems.

An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor

1 code implementation16 May 2020 Riccardo Massa, Alberto Marchisio, Maurizio Martina, Muhammad Shafique

Towards the conversion from a DNN to an SNN, we perform a comprehensive analysis of such process, specifically designed for Intel Loihi, showing our methodology for the design of an SNN that achieves nearly the same accuracy results as its corresponding DNN.

Gesture Recognition Image Classification

DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networks

no code implementations21 Apr 2020 Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique

Many convolutional neural network (CNN) accelerators face performance- and energy-efficiency challenges which are crucial for embedded implementations, due to high DRAM access latency and energy.

Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks

no code implementations15 Apr 2020 Alberto Marchisio, Beatrice Bussolino, Alessio Colucci, Maurizio Martina, Guido Masera, Muhammad Shafique

Capsule Networks (CapsNets), recently proposed by the Google Brain team, have superior learning capabilities in machine learning tasks, like image classification, compared to the traditional CNNs.

Image Classification Quantization

FANNet: Formal Analysis of Noise Tolerance, Training Bias and Input Sensitivity in Neural Networks

no code implementations3 Dec 2019 Mahum Naseer, Mishal Fatima Minhas, Faiq Khalid, Muhammad Abdullah Hanif, Osman Hasan, Muhammad Shafique

With a constant improvement in the network architectures and training methodologies, Neural Networks (NNs) are increasingly being deployed in real-world Machine Learning systems.

General Classification

ReD-CaNe: A Systematic Methodology for Resilience Analysis and Design of Capsule Networks under Approximations

no code implementations2 Dec 2019 Alberto Marchisio, Vojtech Mrazek, Muhammad Abudllah Hanif, Muhammad Shafique

To the best of our knowledge, this is the first proof-of-concept for employing approximations on the specialized CapsNet hardware.

FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activation

no code implementations2 Dec 2019 Le-Ha Hoang, Muhammad Abdullah Hanif, Muhammad Shafique

In this paper, we perform a comprehensive error resilience analysis of DNNs subjected to hardware faults (e. g., permanent faults) in the weight memory.

Autonomous Driving General Classification

ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining

1 code implementation11 Jun 2019 Vojtech Mrazek, Zdenek Vasicek, Lukas Sekanina, Muhammad Abdullah Hanif, Muhammad Shafique

A suitable approximate multiplier is then selected for each computing element from a library of approximate multipliers in such a way that (i) one approximate multiplier serves several layers, and (ii) the overall classification error and energy consumption are minimized.

Multiobjective Optimization

FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule Networks

1 code implementation24 May 2019 Alberto Marchisio, Beatrice Bussolino, Alessio Colucci, Muhammad Abdullah Hanif, Maurizio Martina, Guido Masera, Muhammad Shafique

The goal is to reduce the hardware requirements of CapsNets by removing unused/redundant connections and capsules, while keeping high accuracy through tests of different learning rate policies and batch sizes.

Image Classification Object Detection

autoAx: An Automatic Design Space Exploration and Circuit Building Methodology utilizing Libraries of Approximate Components

no code implementations22 Feb 2019 Vojtech Mrazek, Muhammad Abdullah Hanif, Zdenek Vasicek, Lukas Sekanina, Muhammad Shafique

Because these libraries contain from tens to thousands of approximate implementations for a single arithmetic operation it is intractable to find an optimal combination of approximate circuits in the library even for an application consisting of a few operations.

Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks

no code implementations4 Feb 2019 Alberto Marchisio, Giorgio Nanfa, Faiq Khalid, Muhammad Abdullah Hanif, Maurizio Martina, Muhammad Shafique

We perform an in-depth evaluation for a Spiking Deep Belief Network (SDBN) and a DNN having the same number of layers and neurons (to obtain a fair comparison), in order to study the efficiency of our methodology and to understand the differences between SNNs and DNNs w. r. t.

Data Poisoning

ROMANet: Fine-Grained Reuse-Driven Off-Chip Memory Access Management and Data Organization for Deep Neural Network Accelerators

no code implementations4 Feb 2019 Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique

Our experimental results show that the ROMANet saves DRAM access energy by 12% for the AlexNet, by 36% for the VGG-16, and by 46% for the MobileNet, while also improving the DRAM throughput by 10%, as compared to the state-of-the-art.

CapStore: Energy-Efficient Design and Management of the On-Chip Memory for CapsuleNet Inference Accelerators

no code implementations4 Feb 2019 Alberto Marchisio, Muhammad Abdullah Hanif, Mohammad Taghi Teimoori, Muhammad Shafique

By leveraging this analysis, we propose a methodology to explore different on-chip memory designs and a power-gating technique to further reduce the energy consumption, depending upon the utilization across different operations of a CapsuleNet.

RED-Attack: Resource Efficient Decision based Attack for Machine Learning

no code implementations29 Jan 2019 Faiq Khalid, Hassan Ali, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique

To address this limitation, decision-based attacks have been proposed which can estimate the model but they require several thousand queries to generate a single untargeted attack image.

General Classification Traffic Sign Recognition

CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

no code implementations28 Jan 2019 Alberto Marchisio, Giorgio Nanfa, Faiq Khalid, Muhammad Abdullah Hanif, Maurizio Martina, Muhammad Shafique

Capsule Networks preserve the hierarchical spatial relationships between objects, and thereby bears a potential to surpass the performance of traditional Convolutional Neural Networks (CNNs) in performing tasks like image classification.

Image Classification Traffic Sign Recognition

Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference

no code implementations5 Nov 2018 Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Muhammad Shafique

Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data.

Traffic Sign Recognition

QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks

no code implementations4 Nov 2018 Faiq Khalid, Hassan Ali, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique

Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs).

Quantization

SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters

no code implementations4 Nov 2018 Hassan Ali, Faiq Khalid, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique

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 allowing it to learn the data distribution based on the important edges in the input image.

SIMCom: Statistical Sniffing of Inter-Module Communications for Run-time Hardware Trojan Detection

no code implementations4 Nov 2018 Faiq Khalid, Syed Rafay Hasan, Osman Hasan, Muhammad Shafique

We present a run-time methodology for HT detection that employs a multi-parameter statistical traffic modeling of the communication channel in a given System-on-Chip (SoC), named as SIMCom.

FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning

no code implementations4 Nov 2018 Faiq Khalid, Muhammmad Abdullah Hanif, Semeen Rehman, Junaid Qadir, Muhammad Shafique

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 capability of learning efficiently from large datasets.

Adversarial Attack Traffic Sign Recognition

CapsAcc: An Efficient Hardware Accelerator for CapsuleNets with Data Reuse

no code implementations2 Nov 2018 Alberto Marchisio, Muhammad Abdullah Hanif, Muhammad Shafique

In this paper, we propose CapsAcc, the first specialized CMOS-based hardware architecture to perform CapsuleNets inference with high performance and energy efficiency.

Distributed, Parallel, and Cluster Computing Hardware Architecture

TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks

no code implementations2 Nov 2018 Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique

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 or can be identified during the validation phase.

Autonomous Driving Data Poisoning +4

MPNA: A Massively-Parallel Neural Array Accelerator with Dataflow Optimization for Convolutional Neural Networks

no code implementations30 Oct 2018 Muhammad Abdullah Hanif, Rachmad Vidya Wicaksana Putra, Muhammad Tanvir, Rehan Hafiz, Semeen Rehman, Muhammad Shafique

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 layers much.

A Roadmap Towards Resilient Internet of Things for Cyber-Physical Systems

no code implementations16 Oct 2018 Denise Ratasich, Faiq Khalid, Florian Geissler, Radu Grosu, Muhammad Shafique, Ezio Bartocci

Furthermore, this paper presents the main challenges in building a resilient IoT for CPS which is crucial in the era of smart CPS with enhanced connectivity (an excellent example of such a system is connected autonomous vehicles).

Anomaly Detection Autonomous Vehicles

Cannot find the paper you are looking for? You can Submit a new open access paper.