Xiangyu Qi
Publications by Year
Research Areas
Adversarial Robustness in Machine Learning, Anomaly Detection Techniques and Applications, Security and Verification in Computing, Artificial Intelligence in Healthcare and Education, Scientific Computing and Data Management
Most-Cited Works
- → Visual Adversarial Examples Jailbreak Aligned Large Language Models(2024)86 cited
- → Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks(2021)20 cited
- → Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting(2021)9 cited
- → Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks(2021)2 cited
- → The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege(2025)
- → How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition(2026)