Senior Research Director at Peraton Labs
Dr. Ritu Chadha is a senior research director at Peraton Labs, where she leads the machine learning and data analytics department. She is responsible for basic and applied research programs in the areas of machine learning and artificial intelligence, with applications in a variety of domains, including cyber security, wireless networking, machine vision, text analytics, autonomy, and modeling and simulation.
During her tenure at Peraton Labs and its predecessor companies (Perspecta Labs, Bellcore, Telcordia, Applied Communication Sciences, Vencore Labs), Chadha has performed and managed research in areas at the intersection of cybersecurity, data analytics, machine learning and wireless networking for customers including the Defense Advanced Research Projects Agency (DARPA), U.S. Army Research Laboratory, U.S. Army C5ISR Center, Air Force Research Laboratory, and other government as well as commercial customers.
Chadha is a pioneer in the area of policy-based network management and its application to wireless and mobile ad hoc networks. Chadha’s critical contribution was to leverage the latest advancements in these areas and use them to shape and guide the development of a new suite of successful products for IP network management.
Chadha received a Bachelor of Arts degree in mathematics from St. Stephen’s College, Delhi, India, a Master of Science degree in computer science from Virginia Tech and a doctorate in computer science from the University of North Carolina at Chapel Hill. She has authored more than 100 conference and journal papers, is a coinventor on multiple patents and has written a book on the application of policy-based network management to mobile ad hoc networks. Chadha was elected a Telcordia Fellow in 2008 in acknowledgment of the significance of her contributions to Telcordia’s business in producing both leading edge research and customer-focused results.
Track: Cyber Analytics
Adversarial Machine Learning for Cyber Applications
Over the last few years, it has become evident that machine learning models are vulnerable to different types of attacks. Such attacks, referred to as adversarial machine learning, have been demonstrated in multiple modalities, including images, audio, text, etc., leading to the development of a variety of defensive techniques that mitigate the impact of these attacks. However, the area of adversarial machine learning against the cyber modality is under-explored. This presentation will discuss Adversarial Machine Learning with a focus on cyber applications.