Guangyu Shen
Ph.D. Student
Department of Computer Science, Purdue University
Email: shen447 AT purdue DOT edu
Address: 305 N. University Street, West Lafayette, IN, 47907
About Me
I am currently a fourth year Ph.D. student at the Department of Computer Science at Purdue University, advised by Prof.Xiangyu Zhang. My research interests mainly lie in machine learning security, especially backdoor attacks/defense for AI models under various scenarios(Vision, NLP, etc).
I am also a core member of team Perspecta-PurdueRutgers for the TrojAI competition. Our team ranks top cross rounds 1 to 4, 6 to 10, 12, 13 and 15. Find more info here.
Education
Ph.D., Department of Computer Science, Purdue University, 2020-present
M.S., Polytechnic Institute, Purdue University, 2018-2020
B.S., Software Engineering, University of Electronic Science and Technology of China(UESTC), 2014-2018
News
Jan. 2024: Our paper on removing backdoors in diffusion models got accepted to AAAI 2024.Congrats to Shengwei!
Dec. 2023: Our paper on object detection backdoor scanning got accepted to Oakland 2024.Congrats to Siyuan!
Sep. 2023: Our paper on object detection backdoor scanning got accepted to NeurIPS 2023. Shoutout to all the collaborators!
Sep. 2023: Our paper on detecting NLP posioned samples using LLM got accepted to NeurIPS 2023. Congrats to Lu!
June.2023: Our paper on self-supervised backdoor attack got accepted to Oakland 2024. Congrats to Guanhong!
June.2023: Our paper on hard label black box universal patch attack got accepted to USENIX Security 2023. Congrats to Guanhong!
May.2023: I will join Amazon AWS AI Lab as an applied scientist intern.
Apr.2023: Our paper on physical attack for face recognition system got accepted to Oakland 2023. Congrats to Shengwei!
Apr.2023: Two papers on backdoor removal and detection got accepted to CVPR 2023. Congrats to Qiuling and Shiwei!
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Guangyu Shen*, Siyuan Cheng*, Kaiyuan Zhang, Guanhong Tao, Shengwei An, Lu Yan, Zhuo Zhang, Shiqing Ma, Xiangyu Zhang
Preprint
Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs
Zhuo Zhang, Guangyu Shen, Guanhong Tao, Siyuan Cheng, Xiangyu Zhang
Preprint
Opening A Pandora's Box: Things You Should Know in the Era of Custom GPTs
Guanhong Tao, Siyuan Cheng, Zhuo Zhang, Junmin Zhu, Guangyu Shen, Xiangyu Zhang
Preprint
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang, Qiuling Xu, Guanhong Tao, Guangyu Shen, Siyuan Cheng, Shiqing Ma, Pin-Yu Chen, Tsung-Yi Ho, Xiangyu Zhang
Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024)
ODSCAN: Backdoor Scanning for Object Detection Models
Siyuan Cheng*, Guangyu Shen*, Guanhong Tao, Kaiyuan Zhang, Zhuo Zhang, Shengwei An, Xiangzhe Xu, Yingqi Liu, Shiqing Ma, Xiangyu Zhang
Proceedings of the 45th IEEE Symposium on Security and Privacy (Oakland 2024)
ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP
Lu Yan, Zhuo Zhang, Guanhong Tao, Kaiyuan Zhang, Xuan Cheng, Guangyu Shen, Xiangyu Zhang
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
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
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
Distribution Preserving Backdoor Attack in Self-supervised Learning
Guanhong Tao*, Zhenting Wang*, Shiwei Feng, Guangyu Shen, Shiqing Ma, Xiangyu Zhang
Proceedings of the 45th IEEE Symposium on Security and Privacy (Oakland 2024)
Hard-Label Black-box Universal Adversarial Patch Attack
Guanhong Tao, Shengwei An, Siyuan Cheng, Guangyu Shen, Xiangyu Zhang
Proceedings of the 32nd USENIX Security Symposium (Security 2023)
Improving Binary Code Similarity Transformer Models by Semantics-driven Instruction Deemphasis
Xiangzhe Xu, Shiwei Feng, Yapeng Ye, Guangyu Shen, Zian Su, Siyuan Cheng, Guanhong Tao, Qingkai Shi, Zhuo Zhang, Xiangyu Zhang
Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2023)
Hardening Modern Pre-trained NLP Models Against Backdoors
Guangyu Shen*, Yingqi Liu*, Guanhong Tao, Zhuo Zhang, Qiuling Xu, Shengwei An, Shiqing Ma, Xiangyu Zhang
Preprint
[pdf]
ImU: Physical Impersonating Attack for Face Recognition System with Natural Style Changes
Shengwei An, Yuan Yao, Qiuling Xu, Shiqing Ma, Guanhong Tao, Siyuan Cheng, Kaiyuan Zhang, Yingqi Liu, Guangyu Shen, Ian Kelk, Xiangyu Zhang
Proceedings of the 44rd IEEE Symposiums on Security and Privacy (Oakland 2023)
Remove Model Backdoors via Importance Driven Cloning
Qiuling Xu, Guanhong Tao, Jean Honorio, Yingqi Liu, Shengwei An, Guangyu Shen, Siyuan Cheng, Xiangyu Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR 2023)
[pdf]
Detecting Backdoors in Pre-trained Encoder
Shiwei Feng, Guanhong Tao, Siyuan Cheng, Guangyu Shen, Xiangyu Xu, Yingqi Liu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR 2023)
PELICAN: Exploiting Backdoors of Naturally Trained Deep Learning Models in Binary Code Analysis
Zhuo Zhang, Guanhong Tao, Guangyu Shen, Shengwei An, Qiuling Xu, Yingqi Liu, Yapeng Ye, Yaoxuan Wu, Xiangyu Zhang
Proceedings of the 32nd USENIX Security Symposium (Security 2023)
[pdf]
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
Proceedings of the Eleventh International Conference on Learning Representations (ICLR 2023)
ECCV 2022 Workshop on Adversarial Robustness in the Real World (AROW 2022 Best Paper Award 🏆)
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
Proceedings of the 30th Network and Distributed System Security Symposium (NDSS 2023)
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
Proceedings of the 39th International Conference on Machine Learning (ICML 2022)
PICCOLO: Exposing Complex Backdoors in NLP Transformer Models
Yingqi Liu*, Guangyu Shen*, Guanhong Tao, Shengwei An, Shiqing Ma, Xiangyu Zhang
Proceedings of the 43rd IEEE Symposiums on Security and Privacy (Oakland 2022)
Complex Backdoor Detection by Symmetric Feature Differencing
Yingqi Liu*, Guangyu Shen*, Guanhong Tao, Zhenting Wang, Shiqing Ma, Xiangyu Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022 (CVPR 2022)
Better Trigger Inversion Optimization in Backdoor Scanning
Guanhong Tao, Guangyu Shen, Yingqi Liu, Shengwei An, Qiuling Xu, Shiqing Ma, Pan Li, Xiangyu Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022 (CVPR 2022 Oral)
MIRROR: Model Inversion for Deep Learning Network with High Fidelity
Shengwei An, Guanhong Tao, Qiuling Xu, Yingqi Liu, Guangyu Shen, Yuan Yao, Jingwei Xu, Xiangyu Zhang
Proceedings of the 29th Network and Distributed System Security Symposium (NDSS 2022)
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
Proceedings of the 43rd IEEE Symposiums on Security and Privacy (Oakland 2022)
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
Guangyu Shen*, Yingqi Liu*, Guanhong Tao, Shengwei An, Qiuling Xu, Siyuan Cheng, Shiqing Ma, Xiangyu Zhang
Proceedings of the 38th International Conference on Machine Learning (ICML 2021)
Fooling Semantic Segmentation in One Step via Manipulating Nuisance Factors
Guangyu Shen, Chengzhi Mao, Junfeng Yang, Baishakhi Ray
ECCV 2020 Workshop on Adversarial Robustness in the Real World
[pdf][Conference Page][cite]
Brain tumor segmentation using concurrent fully convolutional networks and conditional random fields
Guangyu Shen, Yi DIng, Tian Lan, Hao Chen, Zhiguang Qin
Proceedings of the 3rd International Conference on Multimedia and Image Processing (ICMIP 2018)
[pdf]
Experience
Applied Scientist Intern, Amazon AWS AI Lab, May.2023-Aug.2023
Research Assistant, working with Prof.Xiangyu Zhang, Purdue University, Jan.2020-present
Research Assistant, working with Prof.Baijian Yang, Purdue University, Aug.2019-Jan.2020
Summer Research Intern, working with Prof.Junfeng Yang and Prof.Baishakhi Ray, Columbia University, May.2019-Aug.2019
Services
Competition Co-chair
IEEE Trojan Removal Competition, 2022
Program Committee
Workshop on Backdoors in Deep Learning: The Good, the Bad, and the Ugly(BUGS), NeurIPS 2023
Workshop on Secure and Trustworthy Deep Learning Systems (SecTL), AsiaCCS 2023
Reviewer
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 2022,2023
International Conference on Machine Learning (ICML): 2022,2023,2024
European Conference on Computer Vision (ECCV): 2022
International Conference on Computer Vision (ICCV): 2023
Conference on Neural Information Processing Systems (NeurIPS): 2022,2023
Sub-reviewer
ACM Conference on Computer and Communications Security (CCS): 2020,2021
ACM Symposium on the Foundations of Software Engineering (FSE): 2020
USENIX Security Symposium: 2022
International Conference on Software Engineering (ICSE): 2022