4 papers
TimeWak: Temporal Chained-Hashing Watermark for Time Series Data
Zhi Wen Soi, Chaoyi Zhu, Fouad Abiad +4
Synthetic time series generated by diffusion models enable sharing privacy-sensitive datasets, such as patients' functional MRI records. Key criteria for synthetic data include hig…
DP-TLDM: Differentially Private Tabular Latent Diffusion Model
Chaoyi Zhu, Jiayi Tang, Juan F. Pérez +2
Synthetic data from generative models emerges as the privacy-preserving data sharing solution. Such a synthetic data set shall resemble the original data without revealing identifi…
Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models
Chaoyi Zhu, Zaitang Li, Renyi Yang +4
Watermarking becomes one of the pivotal solutions to trace and verify the origin of synthetic images generated by artificial intelligence models, but it is not free of risks. Recen…
Duwak: Dual Watermarks in Large Language Models
Chaoyi Zhu, Jeroen Galjaard, Pin-Yu Chen +1
As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms.…