50 citations · 100 across the 10 of their papers we have counts for
10 papers
A Constant-Time Implementation Methodology for Activation Functions on Microcontrollers
Andrii Tyvodar, Andreas Rechberger, Dirmanto Jap +4
Embedded neural-network inference can leak information through timing side channels, including leakage caused by the evaluation of activation functions. This work proposes a consta…
Hardware-Enabled Mechanisms for Verifying Responsible AI Development
Aidan O'Gara, Gabriel Kulp, Will Hodgkins +7
Advancements in AI capabilities, driven in large part by scaling up computing resources used for AI training, have created opportunities to address major global challenges but also…
Side-Channel Analysis of OpenVINO-based Neural Network Models
Dirmanto Jap, Jakub Breier, Zdenko Lehocký +2
Embedded devices with neural network accelerators offer great versatility for their users, reducing the need to use cloud-based services. At the same time, they introduce new secur…
A Desynchronization-Based Countermeasure Against Side-Channel Analysis of Neural Networks
Jakub Breier, Dirmanto Jap, Xiaolu Hou +1
Model extraction attacks have been widely applied, which can normally be used to recover confidential parameters of neural networks for multiple layers. Recently, side-channel anal…
DeepFreeze: Cold Boot Attacks and High Fidelity Model Recovery on Commercial EdgeML Device
Yoo-Seung Won, Soham Chatterjee, Dirmanto Jap +2
EdgeML accelerators like Intel Neural Compute Stick 2 (NCS) can enable efficient edge-based inference with complex pre-trained models. The models are loaded in the host (like Raspb…
Mitigating Power Attacks through Fine-Grained Instruction Reordering
Yun Chen, Ali Hajiabadi, Romain Poussier +3
Side-channel attacks are a security exploit that take advantage of information leakage. They use measurement and analysis of physical parameters to reverse engineer and extract sec…
SNIFF: Reverse Engineering of Neural Networks with Fault Attacks
Jakub Breier, Dirmanto Jap, Xiaolu Hou +2
Neural networks have been shown to be vulnerable against fault injection attacks. These attacks change the physical behavior of the device during the computation, resulting in a ch…
Enhancing Fault Tolerance of Neural Networks for Security-Critical Applications
Manaar Alam, Arnab Bag, Debapriya Basu Roy +4
Neural Networks (NN) have recently emerged as backbone of several sensitive applications like automobile, medical image, security, etc. NNs inherently offer Partial Fault Tolerance…
CSI Neural Network: Using Side-channels to Recover Your Artificial Neural Network Information
Lejla Batina, Shivam Bhasin, Dirmanto Jap +1
Machine learning has become mainstream across industries. Numerous examples proved the validity of it for security applications. In this work, we investigate how to reverse enginee…
DeepLaser: Practical Fault Attack on Deep Neural Networks
Jakub Breier, Xiaolu Hou, Dirmanto Jap +3
As deep learning systems are widely adopted in safety- and security-critical applications, such as autonomous vehicles, banking systems, etc., malicious faults and attacks become a…