Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Get Pro 💎 Log In/Sign Up 🚀

Picture for Shangxi Wu

Shangxi Wu

https://www.catalyzex.com

Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark

May 17, 2023
Wenjun Peng, Jingwei Yi, Fangzhao Wu, Shangxi Wu, Bin Zhu, Lingjuan Lyu, Binxing Jiao, Tong Xu, Guangzhong Sun, Xing Xie

* Accepted by ACL 2023

Access Paper or Ask Questions

Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias

Mar 01, 2023
Shangxi Wu, Qiuyang He, Fangzhao Wu, Jitao Sang, Yaowei Wang, Changsheng Xu

Figure 1 for Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias

Figure 2 for Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias

Figure 3 for Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias

Figure 4 for Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias

Access Paper or Ask Questions

Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias

Feb 18, 2022
Shangxi Wu, Qiuyang He, Yi Zhang, Jitao Sang

Figure 1 for Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias

Figure 2 for Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias

Figure 3 for Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias

Figure 4 for Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias

Access Paper or Ask Questions

An Experimental Study of Semantic Continuity for Deep Learning Models

Nov 19, 2020
Shangxi Wu, Jitao Sang, Xian Zhao, Lizhang Chen

Figure 1 for An Experimental Study of Semantic Continuity for Deep Learning Models

Figure 2 for An Experimental Study of Semantic Continuity for Deep Learning Models

Figure 3 for An Experimental Study of Semantic Continuity for Deep Learning Models

Figure 4 for An Experimental Study of Semantic Continuity for Deep Learning Models

Access Paper or Ask Questions

Adaptive Adversarial Logits Pairing

May 25, 2020
Shangxi Wu, Jitao Sang, Kaiyuan Xu, Guanhua Zheng, Changsheng Xu

Figure 1 for Adaptive Adversarial Logits Pairing

Figure 2 for Adaptive Adversarial Logits Pairing

Figure 3 for Adaptive Adversarial Logits Pairing

Figure 4 for Adaptive Adversarial Logits Pairing

Access Paper or Ask Questions

Butterfly detection and classification based on integrated YOLO algorithm

Jan 02, 2020
Bohan Liang, Shangxi Wu, Kaiyuan Xu, Jingyu Hao

Figure 1 for Butterfly detection and classification based on integrated YOLO algorithm

Figure 2 for Butterfly detection and classification based on integrated YOLO algorithm

Figure 3 for Butterfly detection and classification based on integrated YOLO algorithm

Figure 4 for Butterfly detection and classification based on integrated YOLO algorithm

Access Paper or Ask Questions

blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

Apr 22, 2019
Jiaming Zhang, Jitao Sang, Kaiyuan Xu, Shangxi Wu, Yongli Hu, Yanfeng Sun, Jian Yu

Figure 1 for blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

Figure 2 for blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

Figure 3 for blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

Figure 4 for blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

Access Paper or Ask Questions

Attention, Please! Adversarial Defense via Attention Rectification and Preservation

Nov 24, 2018
Shangxi Wu, Jitao Sang, Kaiyuan Xu, Jiaming Zhang, Yanfeng Sun, Liping Jing, Jian Yu

Figure 1 for Attention, Please! Adversarial Defense via Attention Rectification and Preservation

Figure 2 for Attention, Please! Adversarial Defense via Attention Rectification and Preservation

Figure 3 for Attention, Please! Adversarial Defense via Attention Rectification and Preservation

Figure 4 for Attention, Please! Adversarial Defense via Attention Rectification and Preservation

Access Paper or Ask Questions

Log in or sign up instantly 🚀

🔥 Discover incredible developments in machine intelligence

🤖 Quickly get code for any ML model

🔑 Get help from authors, engineers & researchers

Continue with email

Continue with Google

Continue with Github

Continue with LinkedIn

Continue with Facebook

Continue with Twitter

Seconds away from lift-off 🚀

To ensure authors get your request, sign in to proceed instantly

Continue with email

Continue with Github

Continue with Twitter

Continue with Google

Continue with LinkedIn

Continue with Facebook

© 2023 CatalyzeX

Follow us