Project description
New methods to improve sensitive data security
Data science, machine learning and artificial intelligence are fields that are advancing rapidly. However, the data they want to use and analyse are often sensitive, and protecting them is a difficult challenge. The EU-funded KIProtect project aims to address this challenge with an entirely new, innovative approach for data protection and security that is specifically tailored to Big Data and artificial intelligence. The project will provide a novel data pseudonymisation approach based on modern cryptographic and statistical data transformation methods, allowing customers to easily work with and share sensitive data while ensuring compliance and security.
Objective
The importance of data science, machine learning and artificial intelligence is increasing rapidly. Concepts like smart home, smart cities, connected car, Internet of Things (IoT) and industry 4.0 all require large amounts of data that need to be collected, stored and analyzed. To remain relevant and competitive, companies and public organizations alike need to follow this trend. However, the data they want to use and analyze is often sensitive, and protecting it is a difficult challenge.
KIProtect solves this challenge with an entirely new, innovative approach for data security and data protection that is specifically tailored to big data and artificial intelligence: We provide a novel data pseudonymization approach based on modern cryptographic and statistical data transformation methods. This allows our customers to easily work with and share sensitive data while ensuring compliance and security, enabling them to build data-driven business processes on top of secure data streams. Our technology is currently being tested in several proof of concept (PoC) projects and demonstrably works. It is unique in that it can reliably protect high-dimensional data (e.g. images or time series) while retaining most of the data utility. We therefore have a strong USP and are currently pursuing patent protection for our core algorithm as well, which will grant us a very strong position in the large and fast-growing data security market. We plan to use the H2020 funding to prove the applicability of our approach for specific industries and to develop PoC solutions that enable companies to build secure and robust data processing systems for specific use cases. We have realized a first prototype implementation of our methods as an API and are already working with our first pilot customers to validate our business plan. The European data security market has a volume of more than 1 BN € and grows at 15 % per year. We are confident that we can become a technology leader in it.
Fields of science
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
- engineering and technologycivil engineeringurban engineeringsmart cities
- natural sciencescomputer and information sciencescomputer securitydata protection
- social sciencespolitical sciencespolitical policiescivil society
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringcontrol systemshome automation
- natural sciencescomputer and information sciencesdata sciencedata processing
Programme(s)
Funding Scheme
SME-1 - SME instrument phase 1Coordinator
10707 BERLIN
Germany
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.