171 citations · 294 across the 53 of their papers we have counts for
4 papers · 1 filter
Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis
Jacob Huckelberry, Andrea Mattia Garavagno, Yuke Zhang +3
Most TinyML hardware accelerators focus on supporting Quantized Neural Networks (QNNs) to meet stringent constraints on power consumption and size. Despite this, the security aspec…
TinyML Security: Exploring Vulnerabilities in Resource-Constrained Machine Learning Systems
Jacob Huckelberry, Yuke Zhang, Allison Sansone +3
Tiny Machine Learning (TinyML) systems, which enable machine learning inference on highly resource-constrained devices, are transforming edge computing but encounter unique securit…
Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix
Maximilian Lam, Gu-Yeon Wei, David Brooks +2
We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants give…
EMMA: A New Platform to Evaluate Hardware-based Mobile Malware Analyses
Mikhail Kazdagli, Ling Huang, Vijay Reddi +1
Hardware-based malware detectors (HMDs) are a key emerging technology to build trustworthy computing platforms, especially mobile platforms. Quantifying the efficacy of HMDs agains…