Paper 'TimeWak: Temporal Chained-Hashing Watermark for Time Series Data' accepted as a spotlight paper at NeurIPS 25.
Paper 'Collaborative and Confidential Junction Trees for Hybrid Bayesian Networks' accepted at NeurIPS 25.
Paper 'WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Models' accepted at SIGMOD 26.
Group has three papers accepted at ECML/PKDD 25.
Lydia will serve as DSN 26 TPC co-chairs.
Group has three papers accepted at ARES 25.
Paper 'TabWak: A Watermark for Tabular Diffusion Models' accepted as a spotlight paper at ICLR 25.
Paper 'GTV: Generating Tabular Data via Vertical Federated Learning' accepted at DSN 25.
Research Experience
Currently a professor at University of Neuchatel and TU Delft, and the director of Distributed Learning Systems Lab. Had a decade of industry experience at IBM Research Zurich Lab.
Education
Specific educational background information is not provided.
Background
Research interests include deep learning, distributed systems, and trustworthy technology. Recent research focuses on generative AI systems (how to discover the unknown via the power of generative models) and trustworthy learning systems (how to make learning algorithms robust and verifiable against adversaries that maliciously manipulate data input). After a decade of industry experience at IBM Research Zurich Lab, returned to academia.