Gagandeep Singh

Gagandeep Singh is an Assistant Professor in the Department of Computer Science at the University of Illinois. His research focuses on trustworthy AI, programming languages, and formal methods, with a particular emphasis on ensuring safety, robustness, and ethical alignment in machine learning systems. He holds a Ph.D. from ETH Zurich and has received multiple awards, including the ACM SIGPLAN Doctoral Dissertation Award. His work spans neural network verification, adversarial robustness, and federated learning, with applications in security, reliability, and ethical AI. He has contributed to journal editorships, conferences, and has taught courses on formal methods and trustworthy AI systems.

Education:

• Ph.D. in Computer Science, ETH Zurich (2014–2020)
• Masters in Computer Science, ETH Zurich (2012–2014)
• Bachelor's in Computer Science and Engineering, IIT Patna (2008–2012)

Research Interests:

• Artificial Intelligence Safety & Ethics
• Formal Verification of Neural Networks
• Adversarial Machine Learning
• Federated Learning
• Programming Languages & Static Analysis

Recent Articles: His most recent work addresses challenges in AI alignment, robustness certification, and federated learning optimization, reflecting a focus on both theoretical foundations and practical applications.

Awards & Honors:

• ACM SIGPLAN John C. Reynolds Doctoral Dissertation Award (2021)
• ETH Medal for Best Master's Thesis (2014)

Teaching & Advising: He has taught courses such as 'Formal Software Development Methods' and 'Trustworthy AI Systems', and his research group explores topics like LLM robustness and certified neural networks.