Si Chen
Si Chen was a Ph.D. student in the Bradley Department of Electrical and Computer Engineering. Her advisor was Ruoxi Jia.
Chen’s research focuses primarily on AI safety, with an emphasis on understanding and mitigating risks such as model inversion, privacy leakage, and large language models (LLMs) jailbreak vulnerabilities.
Publications
-
General ItemLabel-Only Model Inversion Attacks via Boundary Repulsion Date: Mar 02, 2022 -
-
General ItemZero-Round Active Learning Date: Jul 14, 2021 -
-
General ItemOne-Round Active Learning Date: Apr 22, 2021 -
Page 1 of 2 | 4 Results
Projects
In the News
-
Article Item
Congratulations to Sanghani Center’s Spring 2025 graduates! , article Date: May 19, 2025 - -
Article Item
Page 1 of 2 | 5 Results