Yuqi Jia

Ph.D. Student at Duke University

yuqi.jia@duke.edu

Bio

Hi! I'm Yuqi Jia, a 4th-year Ph.D. student in ECE at Duke University, advised by Prof. Neil Gong.

My research focuses primarily on AI Security. Recently, I am mainly focused on the following areas:

Before joining Duke, I obtained my B.S. in Computer Science at the ACM Honors Class, Shanghai Jiao Tong University. During my undergrad, I was a research intern at ThinkLab (SJTU) with Prof. Junchi Yan, and also a remote research intern at Mila – Quebec AI Institute with Prof. Jian Tang. More recently, I spent two summers as a research intern at ByteDance Security Flow Team.

Publications

Most recent publications on Google Scholar.
‡ indicates equal contribution.

PromptLocate: Localizing Prompt Injection Attacks

Yuqi Jia, Yupei Liu, Zedian Shao, Jinyuan Jia, Neil Gong

IEEE S&P'26

Competitive Advantage Attacks to Decentralized Federated Learning

Yuqi Jia, Minghong Fang, Neil Gong

NeurIPS'25

Paper

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning

Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang, Neil Gong

NeurIPS'25

Paper

DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks

Yupei Liu, Yuqi Jia, Jinyuan Jia, Dawn Song, Neil Gong

IEEE S&P'25 Distinguished Paper Award

Paper Code

Evaluating Large Language Model based Personal Information Extraction and Countermeasures

Yupei Liu, Yuqi Jia, Jinyuan Jia, Neil Gong

USENIX Security'25

Paper Code

Formalizing and Benchmarking Prompt Injection Attacks and Defenses

Yupei Liu, Yuqi Jia, Runpeng Geng, Jinyuan Jia, Neil Gong

USENIX Security'24

Paper Code

Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents

Yuqi Jia‡, Saeed Vahidian‡, Jingwei Sun, Jianyi Zhang, Vyacheslav Kungurtsev, Neil Gong, Yiran Chen

ECCV'24

Paper Code

PromptLocate: Localizing Prompt Injection Attacks

Yuqi Jia, Yupei Liu, Zedian Shao, Jinyuan Jia, Neil Gong

IEEE S&P'26

Competitive Advantage Attacks to Decentralized Federated Learning

Yuqi Jia, Minghong Fang, Neil Gong

NeurIPS'25

Paper

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning

Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang, Neil Gong

NeurIPS'25

Paper

DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks

Yupei Liu, Yuqi Jia, Jinyuan Jia, Dawn Song, Neil Gong

IEEE S&P'25 Distinguished Paper Award

Paper Code

Evaluating Large Language Model based Personal Information Extraction and Countermeasures

Yupei Liu, Yuqi Jia, Jinyuan Jia, Neil Gong

USENIX Security'25

Paper Code

Formalizing and Benchmarking Prompt Injection Attacks and Defenses

Yupei Liu, Yuqi Jia, Runpeng Geng, Jinyuan Jia, Neil Gong

USENIX Security'24

Paper Code

Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents

Yuqi Jia‡, Saeed Vahidian‡, Jingwei Sun, Jianyi Zhang, Vyacheslav Kungurtsev, Neil Gong, Yiran Chen

ECCV'24

Paper Code

Vitæ

Full Resume in PDF.

Yuqi Jia
yuqi.jia@duke.edu

This website is built with Jekyll using a template by Martin Saveski.