One-and-a-Half-Class Multiple Classifier Systems for Secure Learning Against Evasion Attacks at Test Time

51 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning (2017, background): “4.1.1) [6, 7, 11, 92, 93].”
Adversarial Detection of Flash Malware: Limitations and Open Issues (2017, background): “This notion can also be motivated in formal terms, similarly to the risk analysis reported in [9].”
Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid (2017, background): “5-class classification (based on the combination of anomaly detectors and two-class classifiers) [3] to open-set recognition techniques [23, 2].”
Secure Kernel Machines against Evasion Attacks (2016, background): “In previous work [3], this vulnerability has been referred to as a vulnerability of the classification algorithm.”
On the Security of Machine Learning in Malware C&C Detection (2016, methodology): “Brückner et al. [2012] revise the earlier work of Brückner and Scheffer [2009] to repair the theorem dictating under which conditions a unique Nash equilibrium for a game exists and develop NLR and Nash SVM (NSVM). When tested on email spam detection, the NLR and NSVM variants outperform the non-Nas”