2025

17. Juni

Hardware-accelerated NTT: New Perspective.

Lattice-based Homomorphic Encryption schemes have become the key methodologies for today’s and the future’s secure world. 
It comes at the cost of a vastly increased computational load due to the multiplication of wide-integer coefficient polynomials. NIST recommends Number Theoretic Transform (NTT) as an efficient remedy. Nevertheless, NTT strongly requires acceleration for large numbers of coefficients. We explore a new hardware concept to build NTT accelerators and determine an optimal hardware architecture configuration across various problem sizes.
 

Saleh Mulhem

Download Video

05. Juni

Towards a Unification of Reconstruction Attacks on Syntactic Privacy Models

Syntactic privacy models such as k-anonymity attempt to sanitize data sets such that privacy breaches are prevented. While many attacks are described in the literature, practitioners hesitate to adopt alternatives such as differential privacy, arguing that these attacks rely on exceptional cases which experts avoid in practice. We propose a formal model of syntactic privacy and derive a reconstruction attack which subsumes many existing attacks, thus simplifying the discussion and formal analysis of these attacks.

Niklas Zapatka

Download Video

08. Mai

Towards Learning Differentially Private Probabilistic Relational Models II.

Probabilistic relational models (PRMs) provide a well-established formalism to combine first-order logic and probabilistic models. By reasoning over groups of indistinguishable objects, PRMs abstract from individuals and thus are a promising formalism to generate synthetic relational data that can be made publicly available without violating the privacy of individuals. Building on the previous talk, we take a closer look at how to efficiently learn a PRM from a given propositional probabilistic model.

Malte Luttermann

Download Folien

Download Video

24. April

Towards Learning Differentially Private Probabilistic Relational Models I.

Probabilistic relational models (PRMs) provide a well-established formalism to combine first-order logic and probabilistic models. By reasoning over groups of indistinguishable objects, PRMs abstract from individuals and thus are a promising formalism to generate synthetic relational data that can be made publicly available without violating the privacy of individuals. We investigate how a PRM can be learned from a given propositional probabilistic model and outline the use case of relational data synthesis using PRMs.

Malte Luttermann

Download Folien

Download Video

2024

21. Juni

A Tale of Fully-Homomorphic Encryption and its Applications in Healthcare

Saleh Mulhem

23.Mai

Optimizing for Statistical Independence using a KNN Density Estimator

Kathleen Anderson

11.April

Feature extraction as a primer for privacy-preserving medical data analysis: Example approaches for facial video data

Nele Brügge

14.März

DP Helmet: Distributed Non-Interactive Privacy-Preserving Learning of Convex Optimization problems

Moritz Kirschte

15.Februar

Anon Terminology

 

01.Februar

The Principles of the GDPR (Die Prinzipien der DS-GVO)

Herr Bruegger und Herr Zwingelberg vom ULD (Unabhängiges Landeszentrum für Datenschutz)

Download Video

 

2023

07.Dezember

Uzl-Psychology in AnoMed

Jonas Obleser

 

23.November

Grundlagen FPGAs und FPGA Designs

Christopher Blochwitz

Download Folien

Download Video 

09.November

Grundlagen Clinical studies: currenc concepts, callenges and opportunities

 

Jens Fiehler, CEO of eppdata 

Download Video

26.Oktober

S-GBDT: Differentially Private Training of Gradient Boosting Decision Trees

Thorsten Peinemann und Moritz Kirschte

Download Video

06.Juli

Gaussian Processes and Differential Privacy

Jan Graßhoff, Rabia Demirci, Fraunhofer IMTE

Download Folien

Download Video