About Me
I lead the (newly established) Reliable and Secure AI program at ServiceNow Research . My research intersts and work so far are diverse and cover several research areas and applications, with the common thread through most of my work being the use of mathematical tools (particularly from mathematical optimization and control theory) to improve the robustness and security of real world systems.
Moder AI systems are often best used as assistants. This brings the question: How should AI be designed to best collaborate and communicate with Humans? What are the right modes of communication, and should communication be restricted to specific forms to best facilitate this collaboration? In a series of works from the past few years, we have made progress on understanding this, developing systems that optimally integrate predictions from human clinicians and AI for breast cancer and TB diagnosis, showing how human perception of the AI and AI understanding of human uncertainty affects collaborative performance, and studying the forms human feedback should take when collecting data for AI alignment. AI systems are increasingly deployed in agentic scenarios with access to sensitive information and the ability to take consequentail actions on behalf of a user. These deployments create serious privacy and security risks. Anticipating exactly what attackers may do here is hard as the possiblities increase, and this project seeks to develop mathematical guarantees on the worst case behavior of AI or AI-powered systems. A couple of recent examples is an approach to certifying the robustness of learning algorithms against adaptive and dynamic data poisoning attacks , and the development of superior correlated noise mechanims for differentially private machine learning . This is a nascent project around understanding and improving the ability of multi-agent systems with AI components to trace actions or outputs back to speicifc information sources. Being able to do this reliably and robustly can help deal with hallucinations, incorrect/uncertain predictions or actions, and mitigate certain security risks. Researcher (2017-2024) Researcher (2016-2017) Postdoctoral FellowResearch Interests
Recent Projects
Human AI collaboration and Human Factors in Aligning AI
Certifiably Secure AI
Reliable and Traceable AI
Publications
Past Affiliations
Google DeepMind
Pacific Northwest National Laboratory
Center for Mathematics of Information, Caltech