Shiwei Feng

PhD student, Purdue University

Joined

April 2022

Names

Shiwei Feng (Preferred)

Emails

****@purdue.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

Purdue University (cs.purdue.edu)

2021 – Present

Undergrad student

Nanjing University (smail.nju.edu.cn)

2016 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Xiangyu Zhang

2021 – Present

Expertise

LLM Agent

2024 – Present

Autonomous System

2022 – Present

Backdoor Attack and Defense

2021 – 2023

Publications

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
Xuan Chen, Shiwei Feng, Zikang Xiong, Shengwei An, Yunshu Mao, Lu Yan, Guanhong Tao, Wenbo Guo, Xiangyu Zhang
- NeurIPS 2025 poster
- Readers: Everyone
TAI3: Testing Agent Integrity in Interpreting User Intent
Shiwei Feng, Xiangzhe Xu, Xuan Chen, Kaiyuan Zhang, Syed Yusuf Ahmed, Zian Su, Mingwei Zheng, Xiangyu Zhang
- NeurIPS 2025 poster
- Readers: Everyone
Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
Xuan Chen, Shiwei Feng, Zikang Xiong, Shengwei An, Yunshu Mao, Guanhong Tao, Wenbo Guo, Xiangyu Zhang
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
Zhiyuan Cheng, Zhaoyi Liu, Tengda Guo, Shiwei Feng, Dongfang Liu, Mingjie Tang, Xiangyu Zhang
- ICML 2024 Poster
- Readers: Everyone
ROCAS: Root Cause Analysis of Autonomous Driving Accidents via Cyber-Physical Co-mutation
Shiwei Feng, Yapeng Ye, Qingkai Shi, Zhiyuan Cheng, Xiangzhe Xu, Siyuan Cheng, Hongjun Choi, Xiangyu Zhang
- ASE 2024
- Readers: Everyone
Distribution Preserving Backdoor Attack in Self-supervised Learning
Guanhong Tao, Zhenting Wang, Shiwei Feng, Guangyu Shen, Shiqing Ma, Xiangyu Zhang
- SP 2024
- Readers: Everyone
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
Siyuan Cheng, Guanhong Tao, Yingqi Liu, Guangyu Shen, Shengwei An, Shiwei Feng, Xiangzhe Xu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
Zhiyuan Cheng, Hongjun Choi, Shiwei Feng, James Chenhao Liang, Guanhong Tao, Dongfang Liu, Michael Zuzak, Xiangyu Zhang
- ICLR 2024 poster
- Readers: Everyone
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
Siyuan Cheng, Guanhong Tao, Yingqi Liu, Shengwei An, Xiangzhe Xu, Shiwei Feng, Guangyu Shen, Kaiyuan Zhang, Qiuling Xu, Shiqing Ma, Xiangyu Zhang
- 2023 (modified: 07 Apr 2023)
- NDSS 2023
- Readers: Everyone
Detecting Backdoors in Pre-trained Encoders
Shiwei Feng, Guanhong Tao, Siyuan Cheng, Guangyu Shen, Xiangzhe Xu, Yingqi Liu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
- 2023 (modified: 15 Apr 2023)
- CoRR 2023
- Readers: Everyone

View all 13 publications

Co-Authors

View all 36 co-authors