Hi there 👋 Hello, my name is Wan Qiang.
- 🎓 MS student at Southwest University of Science and Technology (SWUST)
- 🛰️ Next: PhD student at National University of Defense Technology (NUDT) (upcoming)
- 🔬 Research: Adversarial Machine Learning, Interpretable AI (XAI), LLM Security, AI + Simulation Systems
- 🌐 Homepage: https://britney-code.github.io/
- 📫 Contact: 1370192111@qq.com / ww878370@gmail.com
- 🔒 Large Model Security / LLM Safety（大模型安全）
- 🧠 Interpretable Deep Learning / XAI（深度学习可解释性）
- ⚔️ Adversarial Machine Learning（对抗性机器学习）
- 🧩 AI + Systems（AIOS）
I’m passionate about building trustworthy & robust AI systems and exploring why models make decisions.
- PhD student — National University of Defense Technology (NUDT) (2026 – 2030, upcoming)
- MS student — Southwest University of Science and Technology (SWUST) (2023 – 2026)
- Undergraduate — Southwest University of Science and Technology (SWUST) (2019 – 2023)
你可以把你最强的 3~6 个项目放这里（建议：每个项目一句话 + 亮点 + 链接）
-
🔥 Project A — One-line highlight of what it does & why it’s cool.
Tech:PyTorch · XAI · Robustness · Security
👉 Link: https://github.com/britney-code/your-repo -
⚔️ Project B — Adversarial training / attack defense / evaluation benchmark.
Tech:Python · ML · Evaluation
👉 Link: https://github.com/britney-code/your-repo -
🧠 Project C — Interpretable model / explanation method / visualization toolkit.
Tech:XAI · Visualization · Tooling
👉 Link: https://github.com/britney-code/your-repo
如果你暂时不放论文，可以先留占位符，未来补上。
- (Coming soon) — Paper Title, Conference/Journal, Year.
- 📫 Email: 1370192111@qq.com, ww878370@gmail.com
- 🌐 Homepage: https://britney-code.github.io/
More about me (点击展开)
- I enjoy building robust ML systems and researching interpretability for trustworthy AI.
- Open to