Get started
Author

Shangxi Wu

Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark
2023 · Wenjun Peng, Jingwei Yi, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 45
PDF
Robust CAPTCHAs Towards Malicious OCR
2020 · Jiaming Zhang, Jitao Sang, et al. · IEEE Transactions on Multimedia · 25
Butterfly Detection and Classification Based on Integrated YOLO Algorithm
2020 · Bohan Liang, Shangxi Wu, et al. · Advances in intelligent systems and computing · 23
PDF
Prevalence and risk factors of myopia among children and adolescents in Hangzhou
2024 · Lijuan Zhao, Xiujun Jiang, et al. · Scientific Reports · 20
PDF
Attention, Please! Adversarial Defense via Activation Rectification and Preservation
2022 · Shangxi Wu, Jitao Sang, et al. · ACM Transactions on Multimedia Computing Communications and Applications · 8
PDF
Risk factors, lifestyle and prevention among adolescents with spinal curvature abnormality: a cross-sectional study in twenty-four primary and secondary schools in Hangzhou, Zhejiang Province, China
2025 · Lijuan Zhao, Xiujun Jiang, et al. · BMC Public Health · 5
PDF
Adaptive Adversarial Logits Pairing
2023 · Shangxi Wu, Jitao Sang, et al. · ACM Transactions on Multimedia Computing Communications and Applications · 3
PDF
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
2026 · Yuxiang Zhang, Jiangming Shu, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 2
PDF
Backdoor for Debias: Mitigating Model Bias With Backdoor Attack-Based Artificial Bias
2025 · Shangxi Wu, Qiuyang He, et al. · IEEE Transactions on Circuits and Systems for Video Technology · 2
Debiasing backdoor attack: A benign application of backdoor attack in eliminating data bias
2023 · Shangxi Wu, Qiuyang He, et al. · Information Sciences · 2
PDF
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark
2023 · Peng, Wenjun, Yi, Jingwei, et al. · arXiv (Cornell University) · 2
PDF
Prevalence and risk factors of overweight and obesity among children and adolescents in Hangzhou: a cross-sectional study
2026 · Lijuan Zhao, Xiujun Jiang, et al. · BMJ Paediatrics Open · 1
PDF
A Disguised Wolf Is More Harmful Than a Toothless Tiger: Adaptive and Malicious Code Injection Backdoor Attack Leveraging User Behavior as Triggers
2025 · Shangxi Wu, Jinlin Xiao, et al. · IEEE Transactions on Information Forensics and Security · 1
A Disguised Wolf Is More Harmful Than a Toothless Tiger: Adaptive Malicious Code Injection Backdoor Attack Leveraging User Behavior as Triggers
2024 · Wu, Shangxi, Sang, Jitao · arXiv (Cornell University) · 1
PDF
Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-Based Artificial Bias
2024 · Shangxi Wu, Qiuyang He, et al. · SSRN Electronic Journal · 1
An Experimental Study of Semantic Continuity for Deep Learning Models
2020 · Wu, Shangxi, Lu, Dongyuan, et al. · arXiv (Cornell University) · 1
PDF
Attention, Please! Adversarial Defense via Attention Rectification and Preservation.
2018 · Shangxi Wu, Jitao Sang, et al. · arXiv (Cornell University) · 1
Entropic Control for Homeostatic Optimization: Pre-empting Catastrophic Forgetting via Dynamic Feedback
2026 · Wu, Shangxi, Yan, Xiaorong, et al. · arXiv (Cornell University)
PDF
Luminara: Cultural Supervision for Debiasing Cross-Lingual Text-to-Image Generation
2026 · Xiaorong Yan, Shangxi Wu · SSRN Electronic Journal
o1-Coder: an o1 Replication for Coding
2024 · Zhang, Yuxiang, Wu, Shangxi, et al. · arXiv (Cornell University)
PDF
[Comparison and application of obesity screening indicators in children and adolescents aged 6-18 years in Hangzhou in 2023].
2024 · Lijuan Zhao, Bing Zhu, et al. · PubMed
Title：Prevalence and risk factors of overweight and obesity among children and adolescents in Hangzhou: a cross sectional study
2024 · Lijuan Zhao, Xiujun Jiang, et al. · Research Square
Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
2023 · Wu, Shangxi, He, Qiuyang, et al. · arXiv (Cornell University)
PDF
blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness
2019 · Zhang, Jiaming, Sang, Jitao, et al. · arXiv (Cornell University)
PDF
Works count: 24
Citation count: 143
H-index: 5
I10-index: 4
Year
Topic
Type