Xilong Wang

Bio

I'm currently a second-year PhD student in the Department of Electrical and Computer Engineering at Duke University, supervised by Prof. Neil Gong. Prior to that, I earned my Bachelor's degree from the University of Science and Technology of China in 2024.

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

LLM agent security, such as prompt injection attacks to web agents.
Federated learning, including poisoning attacks, defenses, and aggregation algorithms.

News

All

• Aug., 2025    [PAPER] One first-authored paper have been accepted by EMNLP 2025 main!
• Jan., 2025    [PAPER] One first-authored paper have been accepted by ICLR 2025!
• Jan., 2025    [PAPER] One first-authored paper have been accepted by WWW 2025 (Oral)!
• Aug., 2024    [STATUS] I've graduated from USTC and started my PhD jorney at Duke!
• Feb., 2023    [PAPER] One first-authored paper have been accepted by ICASSP 2023!
• Aug., 2022    [STATUS] My homepage is on!

Publications

Most recent publications on Google Scholar.
* indicates equal contribution. ^‡ indicates students mentored by me.

All

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents

Yinuo Liu^‡*, Ruohan Xu^‡*, Xilong Wang*, Yuqi Jia, Neil Zhenqiang Gong

arXiv Preprint, 2025

Paper Code

WebInject: Prompt Injection Attack to Web Agents

Xilong Wang, John Bloch^‡ , Zedian Shao, Yuepeng Hu, Shuyan Zhou, Neil Gong

The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025

Paper

StringLLM: Understanding the String Processing Capability of Large Language Models

Xilong Wang, Hao Fu, Jindong Wang, Neil Gong

International Conference on Learning Representations (ICLR), 2025

Paper Code

Provably Robust Federated Reinforcement Learning

Minghong Fang*, Xilong Wang*, Neil Gong

Proceedings of The Web Conference (WWW), 2025, Oral (Top 7.76%)

Paper

ICStega: Image Captioning-based Semantically Controllable Linguistic Steganography

Xilong Wang, Yaofei Wang, Kejiang Chen, Jinyang Ding, Weiming Zhang, Nenghai Yu

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023

Paper

Academic Service

Reviewer

• Conference: ICLR 2026

• Jornal: IEEE T-IFS

Vitæ

Full Resume in PDF.

Duke University Aug. 2024 – Present

Ph.D. Student
Li Auto Mar. 2024 – Jul. 2024

Research Intern
Duke University Aug. 2022 – Oct. 2023

Undergraduate Researcher
University of Science and Technology of China Sept. 2020 – June. 2024

B.S. Student