I am a third-year Ph.D. student of CUhk REliable Laboratory (CURE), in the Department of Computer Science and Engineering, The Chinese University of Hong Kong, supervised by Prof. Qiang Xu. Our lab is focused on AI security and AI robustness-related tasks. Before that, I got my M. Phil of EE from Tsinghua University in 2019. My current research interests span the fields of AI security and Diffusion models, including Robust Stable Diffusion against Adversarial Attacks and Imperceptible Adversarial Text-to-Image Generation with Natural Prompts.

News

• 🕘 2022-12 International Algorithm Case Competition – Adversarial Defence Competition, 2nd place 🏆
• 🕘 2022-08 Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning has been accepted to ECCV2022 AROW Workshop 👍
• 🕘 2022-07 Out-of-Distribution Detection with Semantic Mismatch under Masking has been accepted to ECCV2022 😃
• 🕘 2021-12 What You See in Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction has been accepted to NDSS2022 CCF-A 👏 (oral, acceptance rate: 14.06%)

Experience

Research Intern
Mar. 2022 - Present, Foundation Model, Megvii, Beijing, China 🇨🇳

Research Intern
Mar. 2020 - June. 2020, 2012 Lab, HUAWEI, Shenzhen, China 🇨🇳

Publications

• Out-of-Distribution Detection with Semantic Mismatch under Masking
  Yijun Yang, Ruiyuan Gao, Qiang Xu
  European Conference on Computer Vision (ECCV), Tel Aviv, Israel, 2022
  code
• Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning
  Zhiyuan He*, Yijun Yang*, Pin-Yu Chen, Qiang Xu, Tsung-Yi Ho
  European Conference on Computer Vision Workshop (ECCV AWOR), Tel Aviv, Israel, 2022
• What You See in Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
  Yijun Yang, Ruiyuan Gao, Yu Li, Qiuxia Lai, Qiang Xu
  Network and Distributed System Security Synposium (NDSS CCF-A), San Diego, California, USA, 2022
  code
• MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
  Yijun Yang, Ruiyuan Gao, Yu Li, Qiuxia Lai, Qiang Xu
  The 48th International Symposium on Computer Architecture (ISCA CCF-A), Secure and Private Systems for Machine Learning Workshop, 2021

Services

I serve as reviewer of conferences: ICASSP, NeurIPS.

Selected Awards and Honors

🏆 Full Postgraduate Studentship, The Chinese University of Hong Kong.
🏆 Outstanding Master Graduate, Tsinghua University (Top 2%).
🏆 Outstanding Thesis Award, Tsinghua University (Top 3%).
🏆 Guanghua Scholarship for Advancement in Academic Work, Tsinghua University (Top 5%).
🏆 Lam Scholarship for Advancement in Academic Work, Tsinghua University (Top 5%).