1 citations · 1 across the 9 of their papers we have counts for
14 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…
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…
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-…
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…
Exploiting Change Blindness for Video Coding: Perspectives from a Less Promising User Study
Mitra Amiri, Steven Le Moan, Christian Herglotz
What the human visual system can perceive is strongly limited by the capacity of our working memory and attention. Such limitations result in the human observer's inability to perc…
Energy Reduction Opportunities in HDR Video Encoding
Christian Herglotz, Steven Le Moan, Alexandre Mercat
This paper investigates the energy consumption of video encoding for high dynamic range videos. Specifically, we compare the energy consumption of the compression process using 10-…