5 papers
Federated Generation of Synthetic RNA-seq Data
Daniil Filienko, Martine De Cock, Sikha Pentyala
Access to genomic data is highly regulated due to its sensitive nature. While safeguards are essential, cumbersome data access processes pose a significant barrier to the developme…
SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)
Steven Golob, Sikha Pentyala, Martine De Cock
Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat ("reconstruction", the recove…
End to End Collaborative Synthetic Data Generation
Sikha Pentyala, Geetha Sitaraman, Trae Claar +1
The success of AI is based on the availability of data to train models. While in some cases a single data custodian may have sufficient data to enable AI, often multiple custodians…
FHAIM: Fully Homomorphic AIM For Private Synthetic Data Generation
Mayank Kumar, Qian Lou, Paulo Barreto +2
Data is the lifeblood of AI, yet much of the most valuable data remains locked in silos due to privacy and regulations. As a result, AI remains heavily underutilized in many of the…
Training Differentially Private Models with Secure Multiparty Computation
Sikha Pentyala, Davis Railsback, Ricardo Maia +4
We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the prote…