How Secure Are Machine Learning Processes?

Wie sicher ist Maschinelles Lernen? Zur Beantwortung dieser Frage werden noch Studienteilnehmerinnen und Studienteilnehmer gesucht. Image Credit: Fraunhofer-Institut für Sichere Informationstechnologie SIT - Participants are needed for a study being conducted by Freie Universität, the Fraunhofer Institute for Applied and Integrated Security (AISEC), the Fraunhofer Institute for Secure Information Technology (SIT), and the National Research Center for App No 137/2020 from Aug 13, 2020 Researchers from Freie Universität, the Fraunhofer Institute for Applied and Integrated Security (AISEC), the Fraunhofer Institute for Secure Information Technology (SIT), and the National Research Center for Applied Cybersecurity (ATHENE) are currently undertaking a joint study to analyze the importance of security and privacy issues to users of machine learning systems. Participants who use machine learning processes in their professional or personal lives are still needed for this research project. Growing numbers of companies are investing in machine learning and artificial intelligence to optimize their internal work processes and offer customers new services by means of recommender systems. "New tools of this type are often rapidly designed and implemented in quick succession. Unfortunately, this tends to mean that security-related issues fall by the wayside," says statistician Verena Battis from Fraunhofer SIT. She studies the risks that machine learning systems pose to data privacy as part of ATHENE's Privacy Risks and Safety in Machine Learning (PRisMa) project.