معرفی
Daniel Kang is an Assistant Professor at the Siebel School of Computing and Data Science, University of Illinois. His research focuses on machine learning systems, cybersecurity for AI models, and database optimization for unstructured data. He specializes in developing robust systems for large language models (LLMs), including defenses against adversarial attacks and benchmarking frameworks for AI agents.
His work bridges machine learning and systems research, addressing challenges such as prompt injection vulnerabilities, zero-day exploit mitigation, and privacy-preserving inference via zero-knowledge proofs. He has contributed to tools like LEAP for processing unstructured data and AIDB for ML-driven databases.
Key collaborations include studies on AI safety, vulnerability exploitation, and ethical AI evaluation. His research outputs emphasize practical applications of ML systems in cybersecurity, data engineering, and interdisciplinary domains like social science analytics.
