I am a Ph.D. candidate in the Institute of Artificial Intelligence, Beihang(BUAA) University , advised by Prof. Xingxing Wei(韦星星) and co-mentored by Prof. Hang Su(苏航) and Dr. Yinpeng Dong(董胤蓬). Before that, I received my B.E. degree in Intelligent Science & Technology from School of Artificial Intelligence, Xidian(XDU) University .

I received the national scholarship in 2021 at Xidian University. I was a research summer intern in 2021 at Digital Team, Dell Technologies(China) Co , mentored by SSE. Xuejin Liang. I was a research intern in 2022 at RealAI , mentored by Dr. Yinpeng Dong.

I’m a AI beginner with interest includes adversarial robustness and natural robustness for deep learning. If you have any suggestions or questions about our works, please feel free to email me: shouweiruan@buaa.edu.cn.

🔥 News

• 2022.02:  ✨ there is no news

📝 Publications

🛩️ Chapter-1: Viewpoint Robustness and Invariance of Visual Systems
In the field of computer vision, viewpoint robustness and invariance present a longstanding challenge. This requires visual models to have the same response or representation to inputs from different viewpoints. To achieve this, we have made a series of efforts, including constructing the first adversarial viewpoint benchmark (ImageNet-V/ImageNet-V+), adversarial viewpoint optimization methods (ViewFool), and adversarial training framework that enhances viewpoint invariance (VIAT). The related work is showcased as follows:

Journal Version, Under Review

Improving Viewpoint Robustness for Visual Recognition via Adversarial Training
Shouwei Ruan, Yinpeng Dong, Hang Su, Jianteng Peng, Ning Chen, Xingxing Wei
💾Project 📃Paper

ICCV2023, Accepted

Towards Viewpoint-Invariant Visual Recognition via Adversarial Training
Shouwei Ruan, Yinpeng Dong, Hang Su, Jianteng Peng, Ning Chen, Xingxing Wei
💾Project 📃Paper

NeurIPS2022, Accepted

ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints
Yinpeng Dong, Shouwei Ruan, Hang Su, Caixin Kang, Xingxing Wei, Jun Zhu
💾Project 📃Paper

🛩️ Chapter-2: Adversarial Robustness: Attack and Defense
We primarily focuses on attack and defense methods against adversarial patches, as well as on the generation of 3D adversarial textures.

CVPR2024, Accepted

Towards Transferable Targeted 3D Adversarial Attack in the Physical World
Yao Huang, Yinpeng Dong, Shouwei Ruan, Xiao Yang, Hang Su, Xingxing Wei
📃Paper

Journal Version, Under Review

Distributional Modeling for Location-Aware Adversarial Patches
Xingxing Wei, Shouwei Ruan, Yinpeng Dong, and Hang Su
💾Project 📃Paper

ECCV2024, Under Review

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks in the Physical World
Caixin Kang, Yinpeng Dong, Zhengyi Wang, Shouwei Ruan, Hang Su, Xingxing Wei
📃Paper

🎖 Honors and Awards

• 2021.10 Lorem ipsum dolor sit amet, consectetur adipiscing elit. Vivamus ornare aliquet ipsum, ac tempus justo dapibus sit amet.
• 2021.09 Lorem ipsum dolor sit amet, consectetur adipiscing elit. Vivamus ornare aliquet ipsum, ac tempus justo dapibus sit amet.

📖 Educations

• 2019.06 - 2022.04 (now), Lorem ipsum dolor sit amet, consectetur adipiscing elit. Vivamus ornare aliquet ipsum, ac tempus justo dapibus sit amet.
• 2015.09 - 2019.06, Lorem ipsum dolor sit amet, consectetur adipiscing elit. Vivamus ornare aliquet ipsum, ac tempus justo dapibus sit amet.

💬 Invited Talks

• 2021.06, Lorem ipsum dolor sit amet, consectetur adipiscing elit. Vivamus ornare aliquet ipsum, ac tempus justo dapibus sit amet.
• 2021.03, Lorem ipsum dolor sit amet, consectetur adipiscing elit. Vivamus ornare aliquet ipsum, ac tempus justo dapibus sit amet. | [video]

💻 Internships

• 2019.05 - 2020.02, Lorem, China.