17 citations · 25 across the 24 of their papers we have counts for
31 papers
Client-Aware Security Adaptive Early Exit Vision Transformers for Heterogeneous Federated Learning
Sahar Refaei Ghalibafan, Samira Nazari, Christian Herglotz +2
Federated learning (FL) trains a shared model across data-owning clients without centralizing raw data, but client data difficulty and compute budgets can differ. We study local ea…
JASPER: Special Session on Joint Reliability And Security Assessment of SPlit Computing for Edge Robustness
Enrico Magliano, Giuseppe Esposito, Amir Hossein Shahdadian +13
Split Computing (SC) enables efficient deployment of Deep Neural Networks (DNNs) by partitioning inference between edge devices and cloud servers. However, intermediate feature rep…
BLADE: ReliaBle Dynamic Hardware-Aware SNN-ANN Boundary SeLection for Event-BAseD Object DEtection
Mahdi Taheri, Alwin Paul
Hybrid Spiking Neural Network (SNN)-Artificial Neural Network (ANN) architectures combine the energy efficiency of SNNs with the superior detection accuracy of ANNs for event-based…
WARD: Runtime Workload-Adaptive Vision TRansformer Framework for Dependable Edge AI
Mahdi Taheri, Pramit Kumar Bhaduri, Mohammad Masoumi +1
Edge-deployed AI operate under dynamically changing power budgets, reliability requirements, and input distributions, requiring continuous adaptation. Such conditions arise in long…
REQAP: Resilient Weight Packing and Quantization for Edge DNN Acceleration
Mahdi Taheri, Samira Nazari, Mubassher Ansari +4
Efficient deployment of Deep Neural Networks (DNNs) on edge accelerators requires aggressive model compression while maintaining reliability in fault-prone hardware environments. T…
PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption
Sahaj Majavdia, Mahdi Taheri
Structured pruning is essential for making neural network inference feasible under homomorphic encryption (HE), yet its impact on model reliability has remained unexplored. This pa…
Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers
Aravind Pradeep, Samira Nazari, Mahdi Taheri +1
Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformati…
HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning
Amir Hossein Shahdadian, Ahmed M. Abdelmoniem, Mahdi Taheri +2
Edge services increasingly use federated learning to personalize on-device models while keeping sensitive data local. In practice, deployments must handle heterogeneity in both cli…
SENTRY: Statistical Reliability Analysis of Vision Transformers Under Soft Errors
Pramit Kumar Bhaduri, Mahdi Taheri, Samira Nazari +3
With the growth of Vision Transformers in safety-critical domains like autonomous systems and medical imaging, ensuring their reliability against soft errors is paramount. While Vi…
Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs
Danial Monachan, Samira Nazari, Mahdi Taheri +4
Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-…
An FPGA-Based SoC Architecture with a RISC-V Controller for Energy-Efficient Temporal-Coding Spiking Neural Networks
Mohammad Javad Sekonji, Ali Mahani, Maryam Mirsadeghi +1
Spiking Neural Networks (SNNs) offer high energy efficiency and event-driven computation, ideal for low-power edge AI. Their hardware implementation on FPGAs, however, faces challe…
RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks
Ali Soltan Mohammadi, Samira Nazari, Ali Azarpeyvand +5
This work proposes a unified three-stage framework that produces a quantized DNN with balanced fault and attack robustness. The first stage improves attack resilience via fine-tuni…
SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI
Parth Patne, Mahdi Taheri, Ali Mahani +3
Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical…
Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators
Atousa Jafari, Mahdi Taheri, Hassan Ghasemzadeh Mohammadi +2
This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model a…
HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs
Samira Nazari, Mohammad Saeed Almasi, Mahdi Taheri +4
This work presents HAWX, a hardware-aware scalable exploration framework that employs multi-level sensitivity scoring at different DNN abstraction levels (operator, filter, layer,…
DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs
Parth Patne, Mahdi Taheri, Christian Herglotz +3
Early-exit deep neural networks enable adaptive inference by terminating computation when sufficient confidence is achieved, reducing cost for edge AI accelerators in resource-cons…
PhD Thesis Summary: Methods for Reliability Assessment and Enhancement of Deep Neural Network Hardware Accelerators
Mahdi Taheri
This manuscript summarizes the work and showcases the impact of the doctoral thesis by introducing novel, cost-efficient methods for assessing and enhancing the reliability of DNN…
SAFFIRA: a Framework for Assessing the Reliability of Systolic-Array-Based DNN Accelerators
Mahdi Taheri, Masoud Daneshtalab, Jaan Raik +5
Systolic array has emerged as a prominent architecture for Deep Neural Network (DNN) hardware accelerators, providing high-throughput and low-latency performance essential for depl…
AdAM: Adaptive Fault-Tolerant Approximate Multiplier for Edge DNN Accelerators
Mahdi Taheri, Natalia Cherezova, Samira Nazari +6
In this paper, we propose an architecture of a novel adaptive fault-tolerant approximate multiplier tailored for ASIC-based DNN accelerators.
Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators
Mahdi Taheri, Natalia Cherezova, Mohammad Saeed Ansari +4
The stringent requirements for the Deep Neural Networks (DNNs) accelerator's reliability stand along with the need for reducing the computational burden on the hardware platforms,…
Enhancing Fault Resilience of QNNs by Selective Neuron Splitting
Mohammad Hasan Ahmadilivani, Mahdi Taheri, Jaan Raik +2
The superior performance of Deep Neural Networks (DNNs) has led to their application in various aspects of human life. Safety-critical applications are no exception and impose rigo…
Special Session: Approximation and Fault Resiliency of DNN Accelerators
Mohammad Hasan Ahmadilivani, Mario Barbareschi, Salvatore Barone +9
Deep Learning, and in particular, Deep Neural Network (DNN) is nowadays widely used in many scenarios, including safety-critical applications such as autonomous driving. In this co…
A Novel Fault-Tolerant Logic Style with Self-Checking Capability
Mahdi Taheri, Saeideh Sheikhpour, Ali Mahani +1
We introduce a novel logic style with self-checking capability to enhance hardware reliability at logic level. The proposed logic cells have two-rail inputs/outputs, and the functi…
APPRAISER: DNN Fault Resilience Analysis Employing Approximation Errors
Mahdi Taheri, Mohammad Hasan Ahmadilivani, Maksim Jenihhin +2
Nowadays, the extensive exploitation of Deep Neural Networks (DNNs) in safety-critical applications raises new reliability concerns. In practice, methods for fault injection by emu…