Lixing Zhang
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes DP-SUM-CUSUM, a differentially private method for detecting synchronized distributional changes across multiple data streams, explicitly characterizing the privacy-efficiency trade-off.
The paper proposes MaskDiff-AD, a forward-only masked diffusion model trained on nominal data to achieve state-of-the-art anomaly detection across various categorical, mixed-type, and text datasets.
Papers
Masked Diffusion Modeling for Anomaly Detection
The paper proposes MaskDiff-AD, a forward-only masked diffusion model trained on nominal data to achieve state-of-the-art anomaly detection across various categorical, mixed-type, and text datasets.