Yugeng Liu

I am a Ph.D. candidate at CISPA Helmholtz Center for Information Security, co-supervised by Prof. Michael Backes and Dr. Yang Zhang. In my current work, I study the worst-case behavior of Deep Learning systems from an adversarial perspective, to understand and mitigate long-term threats to the safety and privacy of users. I was a research intern at Nokia Bell Labs in 2024, where I deepen my research in Trustworthy LLMs.

Prior to joining CISPA, I was a visiting scholar at The Johns Hopkins University (JHU) in 2019, supervised by Prof. Yinzhi Cao. I graduated from Shanghai Jiao Tong University (SJTU) with the Bachelor's degree of Computer Science and Technology in 2018. I spent about two years at NSEC Lab in SJTU, supervised by Prof. Haojin Zhu. My prior work at NSEC Lab focused on novel techniques to enhance the security and privacy of IoT networks.

Download C.V. 

| Research Interests

• Trustworthy Machine Learning, with a focus on LLMs (Safety, Security, and Privacy)
• Misinformation, Hate Speech, and Memes
• IoT Security & Privacy