Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning.
arXiv preprint, Submitted to ICLR 2025
Publications
You can also find my articles on my Google Scholar profile.
arXiv Preprints
Privately Learning from Graphs with Applications in Large Language Model Finetuning.
arXiv preprint, In SFLLM-NeurIPS'24 Workshop.
Conference Papers
Differentially Private Graph Diffusion with Applications in Personalized PageRanks.
Advances in Neural Information Processing Systems (NeurIPS’24)
Learning Scalable Structural Link Representations with Bloom Signatures.
ACM Web Conference (WWW’24)
Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective.
Advances in Neural Information Processing Systems (NeurIPS’22)
Journal Articles
On the Inherent Privacy Properties of Discrete Denoising Diffusion Models.
Transactions on Machine Learning Research (TMLR'24), selected to ICLR 2025 Poster
SLA2P: Self-supervised Anomaly Detection with Adversarial Perturbation.
IEEE Transactions on Knowledge and Data Engineering (TKDE'24)