Zobrazeno 1 - 10
of 665
pro vyhledávání: '"George Kesidis"'
Publikováno v:
Queueing Systems. 103:95-130
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e670363e3ec6dbc0ff49675e7692a700
https://doi.org/10.1007/s11134-022-09852-w
https://doi.org/10.1007/s11134-022-09852-w
Publikováno v:
Proceedings of the 23rd ACM/IFIP International Middleware Conference.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b6a162442f4cc5f23370ae80c6b78e3
https://doi.org/10.1145/3528535.3565245
https://doi.org/10.1145/3528535.3565245
Publikováno v:
Queueing Systems. 100:465-467
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0cdc9ba53b85863849a5858a8f3fb0eb
https://doi.org/10.1007/s11134-022-09833-z
https://doi.org/10.1007/s11134-022-09833-z
Autor:
Hang Wang, Sahar Karami, Ousmane Dia, Hippolyt Ritter, Ehsan Emamjomeh-Zadeh, Jiahui Chen, Zhen Xiang, David J. Miller, George Kesidis
A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small number of samples that each possess the backdoor pattern (usually a pattern
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::60235e0d720c4d92b0cfc57e70779c61
http://arxiv.org/abs/2210.10272
http://arxiv.org/abs/2210.10272
Publikováno v:
Journal of Advanced Research, Vol 5, Iss 4, Pp 423-433 (2014)
We propose a method for detecting anomalous domain names, with focus on algorithmically generated domain names which are frequently associated with malicious activities such as fast flux service networks, particularly for bot networks (or botnets), m
Externí odkaz:
https://doaj.org/article/bd073e14629e444b8c1ab4b1898e4600
Publikováno v:
Future Internet, Vol 11, Iss 3, p 69 (2019)
Network Function Virtualization (NFV) has revolutionized the way network services are offered to end users. Individual network functions are decoupled from expensive and dedicated middleboxes and are now provided as software-based virtualized entitie
Externí odkaz:
https://doaj.org/article/7f84421091c0430c976b2e328deacfe8
Publikováno v:
Neural Computation. 33:1329-1371
Backdoor data poisoning attacks add mislabeled examples to the training set, with an embedded backdoor pattern, so that the classifier learns to classify to a target class whenever the backdoor pattern is present in a test sample. Here, we address po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::316bdbeff9ac4528d508a800ea79795e
https://doi.org/10.1162/neco_a_01376
https://doi.org/10.1162/neco_a_01376
Autor:
Myungjun Son, Shruti Mohanty, Jashwant Raj Gunasekaran, Aman Jain, Mahmut Taylan Kandemir, George Kesidis, Bhuvan Urgaonkar
Publikováno v:
2022 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd1a66bb81dc43cd546efb99cc8f7379
https://doi.org/10.1109/ccgrid54584.2022.00021
https://doi.org/10.1109/ccgrid54584.2022.00021
Publikováno v:
Queueing Systems. 95:203-250
The idea behind the recently introduced "age of information" performance measure of a networked message processing system is that it indicates our knowledge regarding the "freshness" of the most recent piece of information that can be used as a crite
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::252e654a433d29798890128adcd9865f
https://doi.org/10.1007/s11134-020-09655-x
https://doi.org/10.1007/s11134-020-09655-x
Publikováno v:
Proceedings of the IEEE. 108:402-433
With wide deployment of machine learning (ML)-based systems for a variety of applications including medical, military, automotive, genomic, multimedia, and social networking, there is great potential for damage from adversarial learning (AL) attacks.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::565c9ebc22694fa917121f72a899a874
https://doi.org/10.1109/jproc.2020.2970615
https://doi.org/10.1109/jproc.2020.2970615