Works (5)
Updated: April 5th, 2024 13:02
2023 article
Hardware-Software Co-design for Side-Channel Protected Neural Network Inference
2023 IEEE INTERNATIONAL SYMPOSIUM ON HARDWARE ORIENTED SECURITY AND TRUST, HOST, pp. 155–166.
author keywords: machine learning inference; side-channel analysis; masking; flexibility
TL;DR:
This paper develops a secure RISCV-based coprocessor design that can execute a neural network implemented in C/C++ that uses masking to execute various neural network operations like weighted summations, activation functions, and output layer computation in a sidechannel secure fashion.
(via Semantic Scholar)
Source: Web Of Science
Added: August 7, 2023
2022 journal article
Guarding Machine Learning Hardware Against Physical Side-channel Attacks
ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS, 18(3).
author keywords: Side-channel attack; neural networks; masking
TL;DR:
This work develops and combines different flavors of side-channel defenses for ML models in the hardware blocks and proposes and optimize the first defense based on Boolean masking, which impedes a straightforward second-order attack on the first-order masked implementation.
(via Semantic Scholar)
arxiv.org (repository)
Source: Web Of Science
Added: December 5, 2022
2022 article
High-Fidelity Model Extraction Attacks via Remote Power Monitors
2022 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS 2022): INTELLIGENT TECHNOLOGY IN THE POST-PANDEMIC ERA, pp. 328–331.
author keywords: Neural networks; model stealing; time-to-digital converters; secure virtualization
TL;DR:
It is demonstrated that a remote monitor implemented with time-to-digital converters can be exploited to steal the weights from a hardware implementation of NN inference, which expands the attack vector to multi-tenant cloud FPGA platforms.
(via Semantic Scholar)
Source: Web Of Science
Added: November 7, 2022
2020 article
BoMaNet: Boolean Masking of an Entire Neural Network
2020 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED-DESIGN (ICCAD).
author keywords: Masking; neural networks; side-channel attacks; model stealing
TL;DR:
This work proposes the first fully-masked neural network inference engine design and improves the traditional Trichina's AND gates by adding pipelining elements for better glitch-resistance and architecting the whole design to sustain a throughput of 1 masked addition per cycle.
(via Semantic Scholar)
Source: Web Of Science
Added: August 30, 2021
2020 journal article
Characterization of Limit State for Seismic Fragility Assessment of T-Joints in Piping System
JOURNAL OF PRESSURE VESSEL TECHNOLOGY-TRANSACTIONS OF THE ASME, 142(5).
author keywords: seismic fragility; piping; threaded T-joint; limit-state
UN Sustainable Development Goal Categories
11. Sustainable Cities and Communities
(Web of Science)
Source: Web Of Science
Added: September 28, 2020
Citation Index includes data from a number of different sources. If you have questions about the sources of data in the Citation Index or need a set of data which is free to re-distribute, please contact us.
Certain data included herein are derived from the Web of Science© and InCites© (2024) of Clarivate Analytics. All rights reserved. You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.