Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Tamas, Abraham"'
Autor:
Sandamal Weerasinghe, Tamas Abraham, Tansu Alpcan, Sarah M. Erfani, Christopher Leckie, Benjamin I. P. Rubinstein
Publikováno v:
2022 IEEE 61st Conference on Decision and Control (CDC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4575d12d8b1e9f5bd5df387eaf1b3fe5
https://doi.org/10.1109/cdc51059.2022.9992383
https://doi.org/10.1109/cdc51059.2022.9992383
Autor:
Benjamin I. P. Rubinstein, Sarah M. Erfani, Tamas Abraham, Christopher Leckie, Tansu Alpcan, Sandamal Weerasinghe
Publikováno v:
IJCAI
Nonlinear regression, although widely used in engineering, financial and security applications for automated decision making, is known to be vulnerable to training data poisoning. Targeted poisoning attacks may cause learning algorithms to fit decisi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::71b3e9261592063a709254440a1f8bd5
https://doi.org/10.24963/ijcai.2021/437
https://doi.org/10.24963/ijcai.2021/437
Autor:
Yi Han, Olivier De Vel, Paul Montague, Tansu Alpcan, Tamas Abraham, Sarah M. Erfani, Benjamin I. P. Rubinstein, Christopher Leckie, David Hubczenko
Publikováno v:
IJCNN
Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies the problem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c292898b322291e9368266aef167e2e6
https://doi.org/10.1109/ijcnn48605.2020.9206634
https://doi.org/10.1109/ijcnn48605.2020.9206634
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585822
ECCV (27)
ECCV (27)
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges as the mos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3482657160deff51f01a7544433ec4f
https://doi.org/10.1007/978-3-030-58583-9_13
https://doi.org/10.1007/978-3-030-58583-9_13
Ensemble-based adversarial training is a principled approach to achieve robustness against adversarial attacks. An important technique of this approach is to control the transferability of adversarial examples among ensemble members. We propose in th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0123b06bc6de043cde41ccb81dbee574
Autor:
Tamas Abraham, Christopher Leckie, Yi Han, David Hubczenko, Paul Montague, Tansu Alpcan, Sarah M. Erfani, Benjamin I. P. Rubinstein, Olivier De Vel
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030015534
GameSec
GameSec
Despite the successful application of machine learning (ML) in a wide range of domains, adaptability—the very property that makes machine learning desirable—can be exploited by adversaries to contaminate training and evade classification. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::311040586e3bb1e7efc27f95a60d227a
https://doi.org/10.1007/978-3-030-01554-1_9
https://doi.org/10.1007/978-3-030-01554-1_9
Autor:
Tamas Abraham, John F. Roddick
Publikováno v:
GeoInformatica. 3:61-99
Spatio-temporal databases aim to support extensions to existing models of Spatial Information Systems (SIS) to include time in order to better describe our dynamic environment. Although interest into this area has increased in the past decade, a numb
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a27685bd5e460ac927f68fa820a2824
https://doi.org/10.1023/a:1009800916313
https://doi.org/10.1023/a:1009800916313
Autor:
John F. Roddick, Tamas Abraham
Publikováno v:
Advances in Database Technologies ISBN: 9783540656906
ER Workshops
ER Workshops
With the increase in the size of datasets, data mining has become one of the most prevalent topics for research in database systems. The output from this process, the generation of rules of various types, has raised the question of how rules can be c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4ba9b0edbd7b134d69931c3d6c8be509
https://doi.org/10.1007/978-3-540-49121-7_4
https://doi.org/10.1007/978-3-540-49121-7_4
Autor:
Tamas Abraham, John F. Roddick
Publikováno v:
Flinders University PURE
Australasian Journal of Information Systems, Vol 5, Iss 2 (1998)
Australasian Journal of Information Systems, Vol 5, Iss 2 (1998)
Spatial Information Systems and their recent temporal extensions typically store large volumes of geo-referenced information. Having such size, it becomes increasingly difficult to explore their contents with current querying techniques. In this pape
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec4e8c6f6731e4e755c7545eee1170f3
https://doi.org/10.3127/ajis.v5i2.338
https://doi.org/10.3127/ajis.v5i2.338
Autor:
Xiong, Peiyu1 (AUTHOR) gbxpeiyu@ece.ubc.ca, Tegegn, Michael1 (AUTHOR) mtegegn@ece.ubc.ca, Sarin, Jaskeerat Singh1 (AUTHOR) jsarin@student.ubc.ca, Pal, Shubhraneel2 (AUTHOR) shubhraneel@iitkgp.ac.in, Rubin, Julia1 (AUTHOR) mjulia@ece.ubc.ca
Publikováno v:
ACM Computing Surveys. Jul2024, Vol. 56 Issue 7, p1-41. 41p.