50 citations · 313 across the 50 of their papers we have counts for
24 papers · 1 filter
DefensiveDR: Defending against Adversarial Patches using Dimensionality Reduction
Nandish Chattopadhyay, Amira Guesmi, Muhammad Abdullah Hanif +2
Adversarial patch-based attacks have shown to be a major deterrent towards the reliable use of machine learning models. These attacks involve the strategic modification of localize…
ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches
Nandish Chattopadhyay, Amira Guesmi, Muhammad Abdullah Hanif +2
Adversarial attacks present a significant challenge to the dependable deployment of machine learning models, with patch-based attacks being particularly potent. These attacks intro…
A Survey on Quantum Machine Learning: Current Trends, Challenges, Opportunities, and the Road Ahead
Kamila Zaman, Alberto Marchisio, Muhammad Abdullah Hanif +1
Quantum Computing (QC) claims to improve the efficiency of solving complex problems, compared to classical computing. When QC is integrated with Machine Learning (ML), it creates a…
A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
Farzad Nikfam, Raffaele Casaburi, Alberto Marchisio +2
Machine learning (ML) is widely used today, especially through deep neural networks (DNNs), however, increasing computational load and resource requirements have led to cloud-based…
SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation
Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni +1
In this paper, we investigate the vulnerability of MDE to adversarial patches. We propose a novel \underline{S}tealthy \underline{A}dversarial \underline{A}ttacks on \underline{M}D…
X-Rel: Energy-Efficient and Low-Overhead Approximate Reliability Framework for Error-Tolerant Applications Deployed in Critical Systems
Jafar Vafaei, Omid Akbari, Muhammad Shafique +1
Triple Modular Redundancy (TMR) is one of the most common techniques in fault-tolerant systems, in which the output is determined by a majority voter. However, the design diversity…
An Energy-Efficient Generic Accuracy Configurable Multiplier Based on Block-Level Voltage Overscaling
Ali Akbar Bahoo, Omid Akbari, Muhammad Shafique
Voltage Overscaling (VOS) is one of the well-known techniques to increase the energy efficiency of arithmetic units. Also, it can provide significant lifetime improvements, while s…
Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications
Vasileios Leon, Muhammad Abdullah Hanif, Giorgos Armeniakos +4
The challenging deployment of compute-intensive applications from domains such as Artificial Intelligence (AI) and Digital Signal Processing (DSP), forces the community of computin…
Approximate Computing Survey, Part I: Terminology and Software & Hardware Approximation Techniques
Vasileios Leon, Muhammad Abdullah Hanif, Giorgos Armeniakos +4
The rapid growth of demanding applications in domains applying multimedia processing and machine learning has marked a new era for edge and cloud computing. These applications invo…
Reduce: A Framework for Reducing the Overheads of Fault-Aware Retraining
Muhammad Abdullah Hanif, Muhammad Shafique
Fault-aware retraining has emerged as a prominent technique for mitigating permanent faults in Deep Neural Network (DNN) hardware accelerators. However, retraining leads to huge ov…
FAQ: Mitigating the Impact of Faults in the Weight Memory of DNN Accelerators through Fault-Aware Quantization
Muhammad Abdullah Hanif, Muhammad Shafique
Permanent faults induced due to imperfections in the manufacturing process of Deep Neural Network (DNN) accelerators are a major concern, as they negatively impact the manufacturin…
DAP: A Dynamic Adversarial Patch for Evading Person Detectors
Amira Guesmi, Ruitian Ding, Muhammad Abdullah Hanif +2
Patch-based adversarial attacks were proven to compromise the robustness and reliability of computer vision systems. However, their conspicuous and easily detectable nature challen…
SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers
Alberto Marchisio, Davide Dura, Maurizio Capra +3
Transformers' compute-intensive operations pose enormous challenges for their deployment in resource-constrained EdgeAI / tinyML devices. As an established neural network compressi…
RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks
Alberto Marchisio, Antonio De Marco, Alessio Colucci +2
Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships between multiple objects for image classification tasks. Other than achieving high accuracy,…
eFAT: Improving the Effectiveness of Fault-Aware Training for Mitigating Permanent Faults in DNN Hardware Accelerators
Muhammad Abdullah Hanif, Muhammad Shafique
Fault-Aware Training (FAT) has emerged as a highly effective technique for addressing permanent faults in DNN accelerators, as it offers fault mitigation without significant perfor…
RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
To maximize the performance and energy efficiency of Spiking Neural Network (SNN) processing on resource-constrained embedded systems, specialized hardware accelerators/chips are e…
EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems
Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique
Spiking Neural Networks (SNNs) have shown capabilities of achieving high accuracy under unsupervised settings and low operational power/energy due to their bio-plausible computatio…
FPGA-Patch: Mitigating Remote Side-Channel Attacks on FPGAs using Dynamic Patch Generation
Mahya Morid Ahmadi, Lilas Alrahis, Ozgur Sinanoglu +1
We propose FPGA-Patch, the first-of-its-kind defense that leverages automated program repair concepts to thwart power side-channel attacks on cloud FPGAs. FPGA-Patch generates isof…
PoisonedGNN: Backdoor Attack on Graph Neural Networks-based Hardware Security Systems
Lilas Alrahis, Satwik Patnaik, Muhammad Abdullah Hanif +2
Graph neural networks (GNNs) have shown great success in detecting intellectual property (IP) piracy and hardware Trojans (HTs). However, the machine learning community has demonst…
DNN-Alias: Deep Neural Network Protection Against Side-Channel Attacks via Layer Balancing
Mahya Morid Ahmadi, Lilas Alrahis, Ozgur Sinanoglu +1
Extracting the architecture of layers of a given deep neural network (DNN) through hardware-based side channels allows adversaries to steal its intellectual property and even launc…
Exploring Machine Learning Privacy/Utility trade-off from a hyperparameters Lens
Ayoub Arous, Amira Guesmi, Muhammad Abdullah Hanif +2
Machine Learning (ML) architectures have been applied to several applications that involve sensitive data, where a guarantee of users' data privacy is required. Differentially Priv…
scaleTRIM: Scalable TRuncation-Based Integer Approximate Multiplier with Linearization and Compensation
Ebrahim Farahmand, Mohammad Javad Askarizadeh, Ali Mahani +4
In this paper, we propose a scalable approximate multiplier design, scaleTRIM, that approximates the multiplication operation using fitted linear functions, also referred to as lin…
APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigation
Amira Guesmi, Muhammad Abdullah Hanif, Ihsen Alouani +1
In recent times, monocular depth estimation (MDE) has experienced significant advancements in performance, largely attributed to the integration of innovative architectures, i.e.,…
AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systems
Amira Guesmi, Muhammad Abdullah Hanif, Muhammad Shafique
Vision-based perception modules are increasingly deployed in many applications, especially autonomous vehicles and intelligent robots. These modules are being used to acquire infor…