3 papers
cs.LG2018
Security Theater: On the Vulnerability of Classifiers to Exploratory Attacks
Tegjyot Singh Sethi, Mehmed Kantardzic, Joung Woo Ryu
The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These tec…
cs.LG2018
A Dynamic-Adversarial Mining Approach to the Security of Machine Learning
Tegjyot Singh Sethi, Mehmed Kantardzic, Lingyu Lyua +1
Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scena…
cs.LG2018
Handling Adversarial Concept Drift in Streaming Data
Tegjyot Singh Sethi, Mehmed Kantardzic
Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are tradit…