Floragasse 7 – 5th floor, 1040 Vienna
Subscribe to our Newsletter

MLDM

Machine Learning (ML) offers exciting possibilities for innovative products and improvements of existing services. To avoid negative consequences, such as the loss of costumer data or commercial secrets, it is important to consider security and privacy aspects before applying Machine Learning in real-world applications.

SBA Research conducts research in the area of privacy-preserving Machine Learning and develops novel solutions to mitigate related threats. In addition, we offer trainings and expert discussions on implications and available defense mechanisms as well as consulting services in the area of secure and privacy-preserving data management and ML.

Topics include:

  • Protection against theft of intellectual property (data or trained ML models)
  • Defense mechanisms against adversarial attacks
  • Privacy-preserving computation methods like federated learning and secure multi-party computation
  • Novel methods for data anonymization, including complex data types

This content is locked.

By loading this content, you accept YouTube's privacy policy.
https://policies.google.com/privacy

Allow loading YouTube Open on YouTube's website



Research

Machine Learning (ML) offers exciting possibilities for innovative products and improvements of existing services. To avoid negative consequences, such as the loss of costumer data or commercial secrets, it is important to consider security and privacy aspects before applying Machine Learning in real-world applications.

SBA Research conducts research in the area of privacy-preserving Machine Learning and develops novel solutions to mitigate related threats. In addition, we offer trainings and expert discussions on implications and available defense mechanisms as well as consulting services in the area of secure and privacy-preserving data management and ML.

Topics include:

  • Protection against theft of intellectual property (data or trained ML models)
  • Defense mechanisms against adversarial attacks
  • Privacy-preserving computation methods like federated learning and secure multi-party computation
  • Novel methods for data anonymization, including complex data types

With regards to data processing, preserving the privacy of individuals and protecting business secrets is highly relevant for organizations which are working with sensitive and/or personal data. In particular, if companies outsource ML models to external (cloud) providers to analyze their data, they have to consider privacy-preserving data analysis. Data anonymization or -synthetization are possible solutions for privacy protection. A further threat that has to be considered is an adversary recovering training data directly from ML models. SBA Research addresses how organizations can collaboratively build ML models while not directly sharing their data and guaranteeing privacy for their customers.

Automated decision making can have a significant influence on individuals and groups; hence, the robustness of the respective algorithms is of great concern when deploying such systems in real-world applications. Various types of attacks can trick a ML system into making wrong predictions. Backdoor attacks, for instance, poison the training data by injecting carefully designed (adversarial) samples to compromise the whole learning process. In this manner it is possible to, for example: cause classification errors in traffic sign recognition with safety critical implications on autonomous driving; evade spam filters; manipulate predictive maintenance; or circumvent face recognition systems.

Developing methods to detect and defend against these attacks is an important research topic for SBA Research.


Downloads

The Machine Learning and Data Management Research Group participates in the following research projects:

Monitaur

MONITAUR: Monitoring system for copy protection through malicious client detection

Monitaur is an open-source solution for protecting intellectual property of service providers. It is primarily… Read More

Screen4Care

Shortening the path to rare disease diagnosis by using newborn genetic screening and digital technologies

New EU Research Project “Screen4Care”: Accelerating Diagnosis for Rare Disease Patients Through Genetic Newborn Screening… Read More

FeatureCloud

Privacy Preserving Federated Machine Learning and Blockchaining for Reduced Cyber Risks in a World of Distributed Healthcare

The FeatureCloud project develops privacy preserving federated machine learning mechanisms, especially for health-care related settings. Read More

WellFort

WellFort

The WellFort project aims to research the basic mechanisms to provide secure storage for… Read More

GASTRIC

Gene Anonymisation and Synthetisation for Privacy

GASTRIC will investigate three aspects of microbiome sharing and analysis. Read More

PRIMAL

Privacy Preserving Machine Learning for Industrial Applications

PRIMAL will enable industrial deep learning applications by increasing the amount of… Read More

KnoP-2D

Evolving and Securing of Knowledge, Tasks and Processes in Distributed Dynamic Environments via a 2D-Knowledge/Process Graph

Within this project, we develop mechanisms for process mining in a distributed setting, i.e. where… Read More

IPP4ML

Intellectual Property Protection of Machine Learning Processes

IPP4ML will advance the research in the area of intellectual property (IP) protection, with the… Read More

SYNTHEMA

Synthetic generation of haematological data over federated computing frameworks

Under a global lens, the impact of haematological diseases is staggering.Unfortunately, as is common for… Read More

gAia

Predicting landslides - Entwicklung von Gefahrenhinweiskarten für Hangrutschungen aus konsolidierten Inventardaten

The goal of the gAia project is to generate hazard-warning maps for landslides. The project… Read More

SBA-K1 (FP2)

SBA Research - K1 (FP2)

For our second research period from 2021 – 2025, we have devised an ambitious work… Read More

SBA-K1 (FP1)

SBA Research - K1 (FP1)

In our increasingly connected world – where almost all aspects of daily life depend on… Read More

DEXHELPP

Decision Support for Health Policy and Planning: Methods, Models and Technologies based on Existing Health Care Data

The aim of DEXHELPP is the development of new methods, models and technologies to support… Read More

MHMD

My Health – My Data

MyHealthMyData (MHMD) was a Horizon 2020 Research and Innovation Action which aimed at fundamentally changing… Read More

MLDM consists of experts in the areas of privacy-preserving computation, privacy-preserving data publishing, synthetic data, adversarial machine learning, secure learning, detection of and defenses against attacks (e.g., poisoning attacks, evasion attacks), watermarking and fingerprinting of data, and machine learning models.


is FEMtech intern at SBA Research.

is FEMtech intern and researcher at SBA Research.

is researcher at SBA Research.

is senior researcher at SBA Research and leads the Machine Learning and Data Management Research Group. He is a lecturer at TU Wien as well as University of Applied Sciences Technikum Wien.

is senior researcher at SBA Research.

is researcher at SBA Research.

is researcher at SBA Research and PhD student at TU Wien.

is researcher at SBA Research.

is FEMtech intern and researcher at SBA Research.

is researcher at SBA Research.

The following scientific partners and company partners are / have been working closely together with the Machine Learning and Data Management Research Group:


Teaching

The Machine Learning and Data Management Group is also very active in teaching in subjects in their domain at TU Wien. This includes for example the following courses, all at the level of master curricula:


Bachelor | Master | PhD - Thesis Supervision

The MLDM Research Group is supervising Bachelor, Master and PhD theses in the following areas.

  • Adversarial Machine Learning
  • Adversarial Inputs (resp. robustness against adversarial inputs)
  • Backdoor (data poisoning) attacks & defenses
  • Membership inference attack
  • Privacy-preserving Machine Learning / Data Mining
  • Privacy-preserving data publishing
  • Privacy-preserving computation
  • Watermarking/fingerprinting of datasets

Detailed theses information find here.

For further details please contact team lead Rudolf Mayer directly.

To contact the team, please reach out to the individual team members or to the team lead Rudolf Mayer.