There is hope after all: Quantifying opinion and trustworthiness in neural networks

M Cheng, S Nazarian, P Bogdan - Frontiers in artificial intelligence, 2020 - frontiersin.org
Artificial Intelligence (AI) plays a fundamental role in the modern world, especially when
used as an autonomous decision maker. One common concern nowadays is “how …

Trustworthy in silico cell labeling via ensemble-based image translation

S Imboden, X Liu, MC Payne, CJ Hsieh, NYC Lin - Biophysical Reports, 2023 - cell.com
Artificial intelligence (AI) image translation has been a valuable tool for processing image
data in biological and medical research. To apply such a tool in mission-critical applications …

A threat modeling framework for IoT-Based botnet attacks

H **, GH Jeon, HWA Choi, S Jeon, JT Seo - Heliyon, 2024 - cell.com
Abstract Internet of Things (IoT) devices are much closer to users than personal computers
used in traditional computing environments. Due to prevalence of IoT devices, even if they …

Bake it till you make it: Heat-induced power leakage from masked neural networks

DM Mehta, M Hashemi, DS Koblah… - IACR Transactions …, 2024 - ojs.ub.ruhr-uni-bochum.de
Masking has become one of the most effective approaches for securing hardware designs
against side-channel attacks. Regardless of the effort put into correctly implementing …

HWGN2: side-channel protected neural networks through secure and private function evaluation

M Hashemi, S Roy, D Forte, F Ganji - arxiv preprint arxiv:2208.03806, 2022 - arxiv.org
Recent work has highlighted the risks of intellectual property (IP) piracy of deep learning
(DL) models from the side-channel leakage of DL hardware accelerators. In response, to …

[PDF][PDF] Bake It Till You Make It

Masking has become one of the most effective approaches for securing hardware designs
against side-channel attacks. Regardless of the effort put into correctly implementing …