5 papers
How Is Uncertainty Propagated in Knowledge Distillation?
Ziyao Cui, Jian Pei
Knowledge distillation transfers behavior from a teacher to a student model, but the process is inherently stochastic: teacher outputs, student training, and student inference can…
On Membership Inference Attacks in Knowledge Distillation
Ziyao Cui, Minxing Zhang, Jian Pei
Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge dist…
Beyond the Laplacian: Interpolated Spectral Augmentation for Graph Neural Networks
Ziyao Cui, Edric Tam
Graph neural networks (GNNs) are fundamental tools in graph machine learning. The performance of GNNs relies crucially on the availability of informative node features, which can b…
Learning to Attack: Uncovering Privacy Risks in Sequential Data Releases
Ziyao Cui, Minxing Zhang, Jian Pei
Privacy concerns have become increasingly critical in modern AI and data science applications, where sensitive information is collected, analyzed, and shared across diverse domains…
Revisiting Broken Windows Theory
Ziyao Cui, Erick Jiang, Nicholas Sortisio +3
We revisit the longstanding question of how physical structures in urban landscapes influence crime. Leveraging machine learning-based matching techniques to control for demographi…