4 papers
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…
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…
FsimNNs: An Open-Source Graph Neural Network Platform for SEU Simulation-based Fault Injection
Li Lu, Jianan Wen, Milos Krstic
Simulation-based fault injection is a widely adopted methodology for assessing circuit vulnerability to Single Event Upsets (SEUs); however, its computational cost grows significan…