Zobrazeno 1 - 1
of 1
pro vyhledávání: '"António Loison"'
Publikováno v:
Machine Learning and Knowledge Extraction, Vol 2, Iss 4, Pp 558-578 (2020)
Neural network classifiers (NNCs) are known to be vulnerable to malicious adversarial perturbations of inputs including those modifying a small fraction of the input features named sparse or L0 attacks. Effective and fast L0 attacks, such as the wide
Externí odkaz:
https://doaj.org/article/0caf3c18e6ef4c9c8266dd13c62b4509
