Yingqi Liu

Joined

July 2019

Names

Yingqi Liu

Emails

****@purdue.edu (Confirmed)

****@microsoft.com (Confirmed)

****@outlook.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Microsoft (microsoft.com)

2022 – 2025

PhD student

Purdue University (purdue.edu)

2015 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Xiangyu Zhang

2015 – 2022

Expertise

Large language model for security

2022 – 2025

Adversarial Machine Learning

2017 – 2022

Backdoor

2017 – 2022

Trojan attack on neural networks

2017 – 2022

Publications

Combating Hidden Vulnerabilities in Computer Vision Tasks
Guanhong Tao, Siyuan Cheng, Guangyu Shen, Yingqi Liu, Shengwei An, ZHUO ZHANG, Zhenting Wang, Xiangyu Zhang
- ICLR 2025 Conference Withdrawn Submission
- 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- ICLR 2024 Conference Withdrawn Submission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
Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
Guangyu Shen, Siyuan Cheng, Guanhong Tao, Kaiyuan Zhang, Yingqi Liu, Shengwei An, Shiqing Ma, Xiangyu Zhang
- NeurIPS 2023 poster
- Readers: Everyone
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
Kaiyuan Zhang, Guanhong Tao, Qiuling Xu, Siyuan Cheng, Shengwei An, Yingqi Liu, Shiwei Feng, Guangyu Shen, Pin-Yu Chen, Shiqing Ma, Xiangyu Zhang
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- ICLR 2023 poster
- Readers: Everyone
MEDIC: Model Backdoor Removal by Importance Driven Cloning
Qiuling Xu, Guanhong Tao, Jean Honorio, Yingqi Liu, Shengwei An, Guangyu Shen, Siyuan Cheng, Xiangyu Zhang
- 22 Sept 2022 (modified: 13 Feb 2023)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
DECK: Model Hardening for Defending Pervasive Backdoors
Guanhong Tao, Yingqi Liu, Siyuan Cheng, Shengwei An, Zhuo Zhang, Qiuling Xu, Guangyu Shen, Xiangyu Zhang
- 2022 (modified: 05 Nov 2022)
- CoRR 2022
- Readers: Everyone
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
Kaiyuan Zhang, Guanhong Tao, Qiuling Xu, Siyuan Cheng, Shengwei An, Yingqi Liu, Shiwei Feng, Guangyu Shen, Pin-Yu Chen, Shiqing Ma, Xiangyu Zhang
- 2022 (modified: 05 Nov 2022)
- CoRR 2022
- Readers: Everyone
Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Security
Guanhong Tao, Yingqi Liu, Guangyu Shen, Qiuling Xu, Shengwei An, Zhuo Zhang, Xiangyu Zhang
- 2022 (modified: 05 Nov 2022)
- IEEE Symposium on Security and Privacy 2022
- Readers: Everyone
Piccolo: Exposing Complex Backdoors in NLP Transformer Models
Yingqi Liu, Guangyu Shen, Guanhong Tao, Shengwei An, Shiqing Ma, Xiangyu Zhang
- 2022 (modified: 05 Nov 2022)
- IEEE Symposium on Security and Privacy 2022
- Readers: Everyone
Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense
Guangyu Shen, Yingqi Liu, Guanhong Tao, Qiuling Xu, Zhuo Zhang, Shengwei An, Shiqing Ma, Xiangyu Zhang
- 2022 (modified: 05 Nov 2022)
- ICML 2022
- Readers: Everyone

View all 35 publications

Co-Authors

View all 39 co-authors