Zobrazeno 1 - 10
of 158
pro vyhledávání: '"Yunsi Fei"'
Publikováno v:
Frontiers in High Performance Computing, Vol 2 (2024)
The convincing performances of deep neural networks (DNNs) can be degraded tremendously under malicious samples, known as adversarial examples. Besides, with the widespread edge platforms, it is essential to reduce the DNN model size for efficient de
Externí odkaz:
https://doaj.org/article/9cad631153314868ab79bb136115ea76
Publikováno v:
Transactions on Cryptographic Hardware and Embedded Systems, Vol 2020, Iss 2 (2020)
Guessing entropy (GE) is a widely adopted metric that measures the average computational cost needed for a successful side-channel analysis (SCA). However, with current estimation methods where the evaluator has to average the correct key rank over m
Externí odkaz:
https://doaj.org/article/c594039cdf0f4675ae655bfe4047cdcf
Publikováno v:
IEEE Transactions on Information Forensics and Security. 18:3018-3030
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4582c9245fa949886503d5110ac38d18
https://doi.org/10.1109/tifs.2023.3273169
https://doi.org/10.1109/tifs.2023.3273169
Publikováno v:
Proceedings on Privacy Enhancing Technologies, Vol 2022, Iss 1, Pp 501-521 (2022)
Recent advances in machine learning have enabled Neural Network (NN) inference directly on constrained embedded devices. This local approach enhances the privacy of user data, as the inputs to the NN inference are not shared with third-party cloud pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef910d113a96d47ed3dc9caa9860641a
https://doi.org/10.2478/popets-2022-0025
https://doi.org/10.2478/popets-2022-0025
Publikováno v:
Electronic Proceedings in Theoretical Computer Science. 342:35-48
Neural Networks are used today in numerous security- and safety-relevant domains and are, as such, a popular target of attacks that subvert their classification capabilities, by manipulating the network parameters. Prior work has introduced sensitive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fca96cf64018f41d4db50c04be25420a
https://doi.org/10.4204/eptcs.342.4
https://doi.org/10.4204/eptcs.342.4
Publikováno v:
ACM Journal on Emerging Technologies in Computing Systems. 17:1-4
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c1f6c5041df3c728f0368d097aad7178
https://doi.org/10.1145/3464326
https://doi.org/10.1145/3464326
Publikováno v:
Proceedings of the Great Lakes Symposium on VLSI 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::156235c01bfa8f652b2bb5582c84f32c
https://doi.org/10.1145/3526241.3530342
https://doi.org/10.1145/3526241.3530342
Publikováno v:
Proceedings of the Great Lakes Symposium on VLSI 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::137679c2017a9d7f7f792fa2cc9a5d3e
https://doi.org/10.1145/3526241.3530830
https://doi.org/10.1145/3526241.3530830
Publikováno v:
IEEE Transactions on Very Large Scale Integration (VLSI) Systems. 29:124-135
This article presents large delay-based analog Trojan circuits, a new class of analog Trojans that can be interfaced with digital and analog macros to launch fabrication-time hardware attacks. Two different circuit topologies of analog Trojan are pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee34500bc1036306a17a144edb6baaf0
https://doi.org/10.1109/tvlsi.2020.3034878
https://doi.org/10.1109/tvlsi.2020.3034878
Publikováno v:
2022 IEEE International Symposium on Circuits and Systems (ISCAS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::558d4f69d6ae6e8ae36da51d41800051
https://doi.org/10.1109/iscas48785.2022.9937796
https://doi.org/10.1109/iscas48785.2022.9937796