Yalun (Aaron) Wu

Research Interests

My research focuses on AI security: revealing the vulnerabilities of machine-learning-based systems and advocating for robust, trustworthy AI. The specific interests are listed below:

Adversarial Machine Learning

Adversarial attacks and defenses on deep neural networks (DNNs), especially physical-world attacks against perception models.

Autonomous Driving Safety

Security of autonomous driving systems, including traffic sign recognition and pedestrian detection under diverse real-world conditions.

Multimodal LLM Security

Safety and robustness of multimodal large models (LLMs / VLMs), covering jailbreak, backdoor and other emerging threats.

News

2026/06 I obtained the 🎓 Ph.D. degree from Beijing Jiaotong University (BJTU). NEW
2026/06 I was awarded the 🏆 Beijing Outstanding Graduate. NEW
2025/11 🎉 Accepted! One paper has been accepted as Oral by AAAI'26.
2025/11 🎉 Accepted! One paper has been accepted by IOTJ'26.
2024/09 🎉 Accepted! One paper has been accepted by IJIS'24.
2024/09 🎉 Accepted! One paper has been accepted by ADMA'24.
2024/02 🎉 Accepted! One paper has been accepted by IEEE Network'24.
2022/08 Our team won the 🥈 Global Runner-up in the DEF CON'30 Autonomous Driving CTF Challenge. Congratulations! Check out the news from the winning teams: [Our Team@BJTU], [Whitezard@FUDAN].
2022/06 I obtained the 🎓 Master's degree from Beijing Jiaotong University (BJTU).
2022/03 Our team won the 🏆 First Prize in the 2022 Beijing Winter Olympics Vulnerability Discovery. [News]
2022/02 I received 📜 a letter of appreciation from the National Major Network Security Test. [News]
2021/08 Our team won the 🥈 Global Runner-up in the DEF CON'29 Autonomous Driving CTF Challenge. Congratulations! Check out the news from the winning teams: [Our Team@BJTU], [Cacti@UB], [Redbud@THU].
2021/05 🎉 Accepted! One paper has been accepted by ICICS'21.

Selected Publications

* Selected publications are listed below. Full list is on my Google Scholar page.

FRBAT: Conditionally-Visible Physical Backdoor Attack via Fluorescence

Yalun Wu, Liu Liu, Endong Tong, Yingxiao Xiang, Xiaoting Lyu, Zhen Han, Jiqiang Liu.

AAAI'26 CCF-A Oral Paper Code

#Backdoor Attack#Physical Attack#Traffic Sign
FlipBAT: Toward Stealthy Endogenous Backdoor Attacks on Traffic Sign Recognition via Self-Flipping

Yalun Wu, Xiaoshu Cui, Yingxiao Xiang, Yingying Yao, Yuanwan Chen, Zhen Han, Jiqiang Liu, Wenjia Niu.

IOTJ'26 中科院1区CCF-CIF: 8.9 Paper Code

#Backdoor Attack#Traffic Sign Detection
Improving the Robustness of Pedestrian Detection in Autonomous Driving with Generative Data Augmentation

Yalun Wu, Yingxiao Xiang, Endong Tong, Yuqi Ye, Zhibo Cui, Yunzhe Tian, Lejun Zhang, Jiqiang Liu, Zhen Han, Wenjia Niu.

IEEE Network'24 中科院1区IF: 10.2 Paper Code

#Pedestrian Detection#Autonomous Driving
Collaborative Attack Sequence Generation Model Based on Multi-Agent Reinforcement Learning for Intelligent Traffic Signal System

Yalun Wu, Yingxiao Xiang, Thar Baker, Endong Tong, Ye Zhu, Xiaoshu Cui, Zhenguo Zhang, Zhen Han, Jiqiang Liu, Wenjia Niu.

IJIS'24 中科院2区CCF-CIF: 7.0 Paper Code

#Reinforcement Learning#Traffic Signal
Nightfall Deception: A Novel Backdoor Attack on Traffic Sign Recognition Models via Low-Light Data Manipulation

Yalun Wu, Qiong Li, Yingxiao Xiang, Jinkai Zheng, Xingyu Wu, Zhen Han, Jiqiang Liu, Wenjia Niu.

ADMA'24 CCF-C Paper Code

#Backdoor Attack#Low Light#Traffic Sign
Improving Convolutional Neural Network-Based Webshell Detection Through Reinforcement Learning

Yalun Wu, Minglu Song, Yike Li, Yunzhe Tian, Endong Tong, Wenjia Niu, Bowei Jia, Haixiang Huang, Qiong Li, Jiqiang Liu.

ICICS'21 CCF-C Paper Code

#Reinforcement Learning#Webshell Detection
Lurking in the Shadows: Imperceptible Shadow Black-Box Attacks Against Lane Detection Models

Xiaoshu Cui, Yalun Wu, Yanfeng Gu, Qiong Li, Endong Tong, Jiqiang Liu, Wenjia Niu.

KSEM'24 CCF-C Paper Code

#Black-box Attack#Lane Detection
Blockchain-Based Decentralized Federated Learning: A Secure and Privacy-Preserving System

Shuang Zhao, Yalun Wu, Rui Sun, Xiaoai Qian, Dong Zi, Zhiqiang Xie, Endong Tong, Wenjia Niu, Jiqiang Liu, Zhen Han.

HPCC'21 CCF-C Paper Code

#Federated Learning#Blockchain#Privacy

Selected Awards

2025, ZhiJin Scholarship (智瑾奖, 学院唯一获奖者), Beijing Jiaotong University Education Foundation.
2025, First-Class Academic Scholarship (一等学业奖学金), Beijing Jiaotong University.
2025, Excellent Graduate Student Cadre (优秀研究生干部), Beijing Jiaotong University.
2025, Excellent Scholarship in Social Work (社会工作优秀奖学金), Beijing Jiaotong University.
2025, Excellent Part-time Counselor (优秀兼职辅导员), Beijing Jiaotong University.
2024, Advanced Class of Graduate Students Award (研究生先进班集体, 团体奖), Beijing Jiaotong University.
2024, ZhiJin Scholarship (智瑾奖, 学院唯一获奖者), Beijing Jiaotong University Education Foundation.
2024, First-Class Academic Scholarship (一等学业奖学金), Beijing Jiaotong University.
2024, Excellent Graduate Student Cadre (优秀研究生干部), Beijing Jiaotong University.
2024, Excellent Scholarship in Social Work (社会工作优秀奖学金), Beijing Jiaotong University.
2024, Excellent Part-time Counselor (优秀兼职辅导员), Beijing Jiaotong University.
2024, Best Student Paper Award of the Intelligent Vehicles Symposium (智能汽车研讨会最佳学生论文奖), China Computer Federation (CCF).
2023, Advanced Class Award (北京市先进班集体, 团体奖, 全校3个获奖研究生班级之一), Beijing Municipal Commission of Education.
2023, Advanced Class of Graduate Students Award (研究生先进班集体, 团体奖), Beijing Jiaotong University.
2023, Second-Class Academic Scholarship (二等学业奖学金), Beijing Jiaotong University.
2023, Excellent Graduate Student Cadre (优秀研究生干部), Beijing Jiaotong University.
2023, Excellent Scholarship in Social Work (社会工作优秀奖学金), Beijing Jiaotong University.
2022, Admission Academic Scholarship (入学学业奖学金), Beijing Jiaotong University.
2022, Excellent Part-time Counselor (优秀兼职辅导员), Beijing Jiaotong University.
2022, Global Runner-up in the DEF CON'30 Autonomous Driving CTF Challenge, Baidu Security & UCI. [新闻:祝贺计算机学院信息安全系THETA团队在DEFCON30 AutoDriving赛事获得优异成绩]
2022, First Price of the 2022 Beijing Winter Olympics Vulnerability Mining Competition, Peng Cheng Laboratory. [新闻:计算机学院信安团队参与冬奥卫士演练活动荣获一等奖]
2022, A letter of appreciation from the National Major Network Security Test and Assessment Activity, Peng Cheng Laboratory. [新闻:计算机学院信安团队参与国家重大网络安全试验测试活动获感谢信]
2021, Global Runner-up in the DEF CON'29 Autonomous Driving CTF Challenge, Baidu Security & UCI. [新闻: DEF CON 29 Contest自动驾驶CTF赛亚军]

Professional Service

Journal Reviewer: IEEE TIFS, IEEE TDSC, IEEE Network, Pattern Recognition
Conference Committee (PC Member): NeurIPS, IJCAI, ACM MM, AAAI, IJCNN, ADMA