PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction

no code implementations • 5 Oct 2023 • Saifullah Saifullah, Stefan Agne, Andreas Dengel, Sheraz Ahmed

We conduct a comprehensive evaluation of the algorithm across various client and privacy settings, and demonstrate its capability to achieve comparable performance and privacy guarantees to standalone DP, even when accommodating an increasing number of participating clients.

Document AI Federated Learning +1

Privacy Meets Explainability: A Comprehensive Impact Benchmark

no code implementations • 8 Nov 2022 • Saifullah Saifullah, Dominique Mercier, Adriano Lucieri, Andreas Dengel, Sheraz Ahmed

This work is the first to investigate the impact of private learning techniques on generated explanations for DL-based models.

Explainable Artificial Intelligence (XAI) Privacy Preserving +1