Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Kratkiewicz, Kendra"'
Autor:
Severi, Giorgio, Boboila, Simona, Holodnak, John, Kratkiewicz, Kendra, Izmailov, Rauf, De Lucia, Michael J., Oprea, Alina
The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security classification task
Externí odkaz:
http://arxiv.org/abs/2407.08159
Autor:
Severi, Giorgio, Boboila, Simona, Oprea, Alina, Holodnak, John, Kratkiewicz, Kendra, Matterer, Jason
As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor attacks, aga
Externí odkaz:
http://arxiv.org/abs/2306.01655
Autor:
Frisella, Megan, Khorrami, Pooya, Matterer, Jason, Kratkiewicz, Kendra, Torres-Carrasquillo, Pedro
Publikováno v:
Computer Sciences & Mathematics Forum; 2022, Vol. 3, p6, 18p