Adversarial Artificial Intelligence Developing robust AI systems that withstand adversarial attacks — across network security, mobile malware, healthcare AI, and social network manipulation. Robustness across security, health, and social systems Featured research collection → Encrypted Traffic Classification AI-powered classification of encrypted network traffic — enabling security monitoring and QoS management without compromising encryption or user privacy. 100+ application classes; retrieval-based adaptation New Computer Networks paper → Medical Data Science Machine learning for critical care — predicting ICU feeding complications, phenotyping rare respiratory diseases, and enabling privacy-preserving medical data collaboration. Clinical prediction and privacy-preserving collaboration Healthcare AI publications → Incentive Design Mechanism design and game theory for e-commerce platforms, team formation, and kidney exchange — aligning individual incentives with collective outcomes. Mechanisms for platforms, teams, and kidney exchange Mechanism design publications → Quantifying Constructivist Learning in Studio-Based Education Data science methods that quantify learning in design studio education — measuring cognitive breakthroughs, engagement, and teaching effectiveness during live critiques. Live-critique learning signals quantified Education publications → A Multimodal Approach for Measuring Item Similarity Multimodal AI that fuses computer vision and NLP to measure item similarity the way humans do — powering smarter recommendations in tourism, e-commerce, and real estate. Vision + language + time for product similarity Multimodal research →
