I am Associate Professor of Information Sciences and Technology at Penn State and a part-time research scientist at Meta. I conduct research at the interface of machine learning, privacy, and security. I direct the Algorithmic Learning, Privacy, and Security (ALPS) Lab. The overarching goal of my research is to maximize the practical impact of artificial intelligence (AI) by bridging technological advances and transformative applications. To this end, my recent work focuses on improving AI technologies along three major thrusts:
Security Assurance – resilient against malicious manipulations
Privacy Preservation – respectful for individual privacy
Decision-Making Transparency – interpretable to human perception
I joined Penn State in Fall 2019. I received my doctoral degree from Georgia Tech and finished my undergrad study at Zhejiang University (China).
AutoML in the Wild (CHI '23) interviews real-world users to understand the limitations they face in using AutoML, how they work around such obstacles, and their expectations for future advances of AutoML.
The Dark Side of AutoML (ICLR '23) explores the possibility of exploiting AutoML as a new attack vector to launch previously improbable attacks (i.e., backdoors hidden in neural network architectures).
AIRS (USENIX '23) faithfully explains the most critical steps in deep reinforcement learning with a range of security applications (e.g., autonomous driving).
📪 E369 Westgate Building, University Park, PA 16802
We are ALWAYS looking for motivated and bright (under)grad students and postdocs. If you know how to build/hack AI systems, we should talk! Please email me your resume and set up a time to discuss your potential fit to our team.