Mojan Javaheripi

HASHTAG: Hash Signatures for Online Detection of Fault-Injection Attacks on Deep Neural Networks

2021 · arXiv (Cornell University)

We propose HASHTAG, the first framework that enables high-accuracy detection of fault-injection attacks on Deep Neural Networks (DNNs) with provable bounds on detection performance. Recent literature in fault-injection attacks shows the severe DNN accuracy degradation …

AdaGL: Adaptive Learning for Agile Distributed Training of Gigantic GNNs

2023

Distributed GNN training on contemporary massive and densely connected graphs requires information aggregation from all neighboring nodes, which leads to an explosion of inter-server communications. This paper proposes AdaGL, a highly scalable end-to-end framework for …