On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks
arXiv: Learning, Volume abs/1809.02861, 2018.
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Studying transferability of attacks has gained interest in the last years due to the deployment of cyber-attack detection services based on machine learning. For these applications of machine ...More
Full Text (Upload PDF)
PPT (Upload PPT)