Dr. Ian Molloy is a Principal Research Staff Member and Manager of the Cognitive Security Services group in the Security Department at IBM's Thomas J. Watson Research Center. He currently leads IBM Research's efforts on securing AI systems against new threats to the confidentiality and integrity of enterprise AI systems, privacy of sensitive training data, and adversarial samples. He also serves as the Cybersecurity Theme Lead for the MIT-IBM Watson AI Lab where he is the co-PI on several projects. His primary research interest is in the application of machine learning to problems in security and privacy and to the protection of AI. His recent research is on protecting machine learning models with a focus on adversarial samples, poisoning, and model theft attacks. Current and prior work includes analytics for the detection of transactional fraud, insider threat, IoT and container security, cloud security, and access control. His work has been included in IBM products and offerings such as the QRadar User Behavior Analytics application. He received his PhD from Purdue University in 2010 working under Dr. Ninghui Li in the Center for Education and Research in Information Assurance and Security.
AI/Machine Learning/Deep Learning