Varun Chandrasekaran

Varun Chandrasekaran is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Illinois' Grainger College of Engineering. His research focuses on computer security, privacy, and information trust, with a growing emphasis on AI ethics and governance. He teaches courses including Computer Security I & II (CS 461/463) and Advanced Topics in Security, Privacy, and Machine Learning (CS 562). His work addresses critical challenges in generative AI security, adversarial machine learning, and privacy-preserving technologies.

Dr. Chandrasekaran's research highlights include analyzing risks of AI models like OpenAI's Strawberry, advocating for transparent AI development, and proposing solutions like machine unlearning frameworks (e.g., Amun). His contributions span theoretical advancements and practical applications, such as secure code translation and watermarking defenses. He emphasizes peer-reviewed security practices over proprietary solutions, aligning with cryptographic principles for reliability.

Recent projects explore multimodal data curation (MM-GEN), bias mitigation in LLMs, and automated benchmarking (Benchagents). His work bridges academic research with real-world cybersecurity needs, addressing threats from adversarial actors exploiting AI capabilities. Chandrasekaran frequently collaborates with industry and policy experts to shape ethical AI frameworks and standards.