Guangyu Shen
Computer Science · Purdue University West Lafayette
Publications
26
Citations
370
Est. group size
~8
Recurring co-author estimate
Active years
20
Publishing since 2007
Guangyu Shen works on the security and reliability of machine learning systems, including detecting adversarial attacks (deliberately crafted inputs meant to fool AI models), identifying malware and anomalies, and detecting deepfakes (AI-generated fake images or videos). Earlier work also applied deep learning to medical image analysis, such as segmenting brain tumors in scans. This research is relevant to students interested in making AI systems more robust, secure, and trustworthy.
Publication output has grown from about 1 paper per year in 2017-2018 to a peak of 6 in 2023, with continued activity of 2-3 papers per year through 2025-2026, indicating an overall increasing trend over the decade.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- AuthGuard: Generalizable Deepfake Detection via Language Guidance
2026
- Unrestricted Adversarial Attacks For Semantic Segmentation
arXiv (Cornell University) · 2019
- AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
arXiv (Cornell University) · 2019
- Brain Tumor Segmentation Using Concurrent Fully Convolutional Networks and Conditional Random Fields
2018
- Multi‐modal brain tumor image segmentation based on SDAE
International Journal of Imaging Systems and Technology · 2017
- arXiv (Cornell University)×7
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)×2
- 2022 IEEE Symposium on Security and Privacy (SP)×2
- International Journal of Imaging Systems and Technology×1
- International Conference on Machine Learning×1
- Shengwei An
Computer Science · Purdue University West Lafayette
- Guanhong Tao
Computer Science · Indiana University
- Qiuling Xu
Computer Science · Purdue University West Lafayette
- Wenbo Guo
Computer Science · Purdue University West Lafayette
- Qi Alfred Chen
Computer Science · Purdue University West Lafayette
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile