Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Ismail Alkhouri"'
Publikováno v:
Circuits, Systems, and Signal Processing. 42:2385-2415
Minimally perturbed adversarial examples were shown to drastically reduce the performance of one-stage classifiers while being imperceptible. This paper investigates the susceptibility of hierarchical classifiers, which use fine and coarse level outp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::505a6a1ef0a8fb3d48f9094a8318d885
https://doi.org/10.1007/s00034-022-02226-w
https://doi.org/10.1007/s00034-022-02226-w
Autor:
Alvaro Velasquez, Brett Bissey, Lior Barak, Daniel Melcer, Andre Beckus, Ismail Alkhouri, George Atia
Publikováno v:
Proceedings of the International Conference on Automated Planning and Scheduling. 32:652-661
Sparse rewards and their representation in multi-agent domains remains a challenge for the development of multi-agent planning systems. While techniques from formal methods can be adopted to represent the underlying planning objectives, their use in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5001d4c0f99de47bb6d62c966790ba1a
https://doi.org/10.1609/icaps.v32i1.19854
https://doi.org/10.1609/icaps.v32i1.19854
Publikováno v:
Journal of Automated Reasoning. 67
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b360e60f4b596bb9a66aebe86b06b638
https://doi.org/10.1007/s10817-022-09657-9
https://doi.org/10.1007/s10817-022-09657-9
Autor:
Alvaro Velasquez, Brett Bissey, Lior Barak, Andre Beckus, Ismail Alkhouri, Daniel Melcer, George Atia
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:12015-12023
Reinforcement learning and planning have been revolutionized in recent years, due in part to the mass adoption of deep convolutional neural networks and the resurgence of powerful methods to refine decision-making policies. However, the problem of sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3218288d307917c7030bdc819b29a694
https://doi.org/10.1609/aaai.v35i13.17427
https://doi.org/10.1609/aaai.v35i13.17427
Publikováno v:
MLSP
The study of robustness of deep classifiers has exposed their vulnerability to perturbation attacks. Prior work has largely focused on adversarial attacks targeting one-stage-classifiers. By contrast, here we investigate the susceptibility of Nested
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e18d7859e21965bb4869f650429469f0
https://doi.org/10.1109/mlsp52302.2021.9596336
https://doi.org/10.1109/mlsp52302.2021.9596336
Publikováno v:
MLSP
Building automation systems are susceptible to malicious attacks, causing erroneous Fault Detection and Diagnosis (FDD). In this paper, we aim at examining the robustness of a Hierarchical Fault Detection and Diagnosis (HFDD) model, which uses multip
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dfa450ac5a31a75c0cb37347f7cf78ec
https://doi.org/10.1109/mlsp52302.2021.9596378
https://doi.org/10.1109/mlsp52302.2021.9596378
Autor:
George K. Atia, Ismail Alkhouri
Publikováno v:
IJCNN
Adversarial attacks were shown to drastically degrade the performance of one-stage classifiers while being undetectable. In this paper, we examine the susceptibility of both flat and top-down hierarchical classifiers, abbreviated FHCs and TDHCs respe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::78eab19b666df2beeb10673d10bef773
https://doi.org/10.1109/ijcnn52387.2021.9534154
https://doi.org/10.1109/ijcnn52387.2021.9534154
Autor:
George K. Atia, Ismail Alkhouri
Publikováno v:
ICASSP
Adversarial attacks have exposed the vulnerability of one-stage classifiers to carefully crafted perturbations which were shown to drastically alter their predictions while remaining imperceptible. In this paper, we examine the susceptibility of coar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b9b61170d63670259060586eaea2289
https://doi.org/10.1109/icassp39728.2021.9413743
https://doi.org/10.1109/icassp39728.2021.9413743
The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies formal specifications in the form of some well-defined logic. While m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb9cf7794ea3a23a937a22b4df3020c8
http://arxiv.org/abs/2012.02178
http://arxiv.org/abs/2012.02178
Publikováno v:
ISCAS
Existing work on adversarial attacks on classification tasks has focused on classifiers that make use of simple hypothesis testing models. In this work, we study the vulnerability of composite classifiers employing generalized likelihood ratio tests
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3295949f83b3076d19ebf9276a3c0b9c
https://doi.org/10.1109/iscas45731.2020.9180821
https://doi.org/10.1109/iscas45731.2020.9180821