Mijin Koo

I am a Ph.D. student in the Department of Intelligence and Information at Seoul National University, advised by Prof. Nojun Kwak in the Machine Intelligence and Pattern Recognition Lab (MIPAL). Currently, I am a Visiting Scholar in the School of Computer Science (S3D) at Carnegie Mellon University, fully funded by an IITP fellowship from the Korean Ministry of Science and ICT.

My research focuses on the safety and security of generative and embodied AI, including adversarial robustness, data protection for diffusion models, and runtime safeguards for VLM-based agents. Previously, I worked as an AI Researcher at AIM Intelligence, where I developed VLM-based runtime safeguards for physical AI agents and deployed them on a Unitree G1 humanoid robot.

I received my B.S. in Computer Science and Engineering from Ewha Womans University. During my undergraduate studies, I worked as a Research Intern at the Korea Institute of Science and Technology (KIST), developing adversarial defense methods based on diffusion models.

I am always open to discussing new research ideas. Please feel free to contact me via email or LinkedIn.