Feng Chen

Feng Chen is an Associate Professor in the Department of Computer Science at The University of Texas at Dallas (UT Dallas), part of the Erik Jonsson School of Engineering & Computer Science. He directs the AI Safety Laboratory and holds tenure. His research focuses on AI safety, ethical machine learning, uncertainty quantification, and fair algorithms. He earned a Ph.D. from Virginia Tech (2012), M.S. from Beijing University of Aeronautics & Astronautics (2004), and B.S. from Hunan University (2001).

His research spans AI safety frameworks, resilient AI systems, fairness in healthcare and finance, cybersecurity, and environmental AI applications. Key contributions include uncertainty-aware deep learning, causal representation learning, and adversarial vulnerability analysis. He has authored over 150 peer-reviewed publications, including top venues like NeurIPS, ICML, KDD, and ICDM.

• Grants: $4.2M+ in funding from NSF, Army Research Office, IARPA, and industry partners.
• Teaching: Courses in data mining, anomaly detection, and artificial intelligence since 2014.

Notable achievements include an NSF CAREER Award (2018) and leadership in projects like EMBERS (social media event prediction). His work bridges theory and practice, addressing societal challenges through ethical AI principles.

Labs/Teams: AI Safety Laboratory (UT Dallas), collaborative projects with Virginia Tech, Carnegie Mellon, and industry partners on software vulnerability analysis and causal AI.

Awards: Multiple best paper nominations, including 2nd Place in NAE Security Category (2009) and UT Dallas Outstanding Research (2021-2022).