Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Ziv Katzir"'
Publikováno v:
Knowledge-Based Systems. 242:108377
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0f2db9573dd3db5375a01dd40bcc01b1
https://doi.org/10.1016/j.knosys.2022.108377
https://doi.org/10.1016/j.knosys.2022.108377
Autor:
Yuval Elovici, Ziv Katzir
Publikováno v:
IEEE transactions on neural networks and learning systems. 32(1)
Despite their accuracy, neural network-based classifiers are still prone to manipulation through adversarial perturbations. These perturbations are designed to be misclassified by the neural network while being perceptually identical to some valid in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1bc80df1227b0fffb779088b93d9eeb
https://pubmed.ncbi.nlm.nih.gov/32167916
https://pubmed.ncbi.nlm.nih.gov/32167916
Autor:
Rami Puzis, Ziv Katzir, Edita Grolman, Asaf Shabtai, Liron Rosenfeld, Gershon Celniker, Andrey Finkelshtein
Publikováno v:
IEEE Intelligent Systems. 33:40-53
Recent academic studies have demonstrated the possibility of inferring user actions performed in mobile apps by analyzing the resulting encrypted network traffic. Due to the multitude of app versions, mobile operating systems, and device models (coll
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de8e25e4fc0f086337426e298db59848
https://doi.org/10.1109/mis.2018.111145120
https://doi.org/10.1109/mis.2018.111145120
Autor:
Ziv Katzir, Yuval Elovici
Publikováno v:
Expert Systems with Applications. 92:419-429
The use of machine learning algorithms for cyber security purposes gives rise to questions of adversarial resilience, namely: Can we quantify the effort required of an adversary to manipulate a system that is based on machine learning techniques? Can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba3ce8d36d8e20df19295455d86ff11b
https://doi.org/10.1016/j.eswa.2017.09.053
https://doi.org/10.1016/j.eswa.2017.09.053