Secure Machine Learning Hardware: Challenges and Progress [Feature]

K Lee, M Ashok, S Maji, R Agrawal… - IEEE Circuits and …, 2025 - ieeexplore.ieee.org
With the rising adoption of deep neural networks (DNNs) for commercial and high-stakes
applications that process sensitive user data and make critical decisions, security concerns …

An energy-efficient neural network accelerator with improved resilience against fault attacks

S Maji, K Lee, C Gongye, Y Fei… - IEEE Journal of Solid …, 2024 - ieeexplore.ieee.org
Embedded neural network (NN) implementations are vulnerable to misclassification under
fault attacks (FAs). Clock glitching and injecting strong electromagnetic (EM) pulses are two …

Neurosec: Fpga-based neuromorphic audio security

M Isik, H Vishwamith, Y Sur, K Inadagbo… - … Symposium on Applied …, 2024 - Springer
Neuromorphic systems, inspired by the complexity and functionality of the human brain,
have gained interest in academic and industrial attention due to their unparalleled potential …

SparseLeakyNets: Classification Prediction Attack Over Sparsity-Aware Embedded Neural Networks Using Timing Side-Channel Information

S Maji, K Lee, AP Chandrakasan - IEEE Computer Architecture …, 2024 - ieeexplore.ieee.org
This letter explores security vulnerabilities in sparsity-aware optimizations for Neural
Network (NN) platforms, specifically focusing on timing side-channel attacks introduced by …