Keywords: AI and Machine Learning,
Adversarially Robust Machine LearningSadia Afroz, Senior Researcher, International Computer Science Institute, UC Berkeley
Machine learning provides valuable methodologies for detecting and protecting against security attacks at scale. However, a machine-learning algorithm used for security is different from other domains because in a security setting, an adversary will try to adapt his behavior to avoid detection. This research team will explore methodologies for improving the robustness of a machine-learning classifier. This work will improve the understanding of the brittleness of machine-learning solutions and provide guidelines for improvement.