Who we are
CERTAIN stands for “Center for European Research in Trusted AI” and focuses on an approach that highlights the issue of “trust” in AI systems – an aspect that is often neglected in international research. The aim is to develop new technologies that provide functional and other guarantees for AI systems.
CERTAIN is a consortium, a collaborative initiative involving various partners, legally part of DFKI, focused on researching, developing, deploying, standardizing, and promoting Trusted AI techniques, with the aim of providing guarantees for and certification of AI systems, and it allows for project collaboration with both internal and external partners.
What we do
Research
Defragmentation
Application
Communication
Current News
KI + Autoritarismus – Wie KI politische Macht verändert, Kontrolle ausübt und Demokratien herausfordert.
On 29 May 2026, CERTAIN, together with Algoright e.V., the Landeszentrale für politische Bildung Saarland and Dock 11, hosted a public evening event in Saarbrücken. Artificial intelligence is transforming political systems worldwide – from state surveillance to the targeted manipulation of public opinion. In authoritarian contexts, AI is deliberately used to consolidate power, suppress opposition […]
CERTAIN @ Presseclub Saar: AI and Journalism.
On 27 May 2026, Dr. Kevin Baum, our researcher and Executive Board member, joined Presseclub Saar in Saarbrücken for an evening on artificial intelligence and journalism. Under the title “AI and Journalism: Between Tool, Weapon and Competitor”, the discussion explored how AI technologies are already affecting information quality, opinion formation, and trust in media. Baum […]
CERTAIN @ 1st CLaRAMAS Workshop at AAMAS.
CERTAIN was proud to be represented at the 1st International Workshop on Causal Learning and Reasoning in Agents and Multiagent Systems — CLaRAMAS — through our researcher André Meyer-Vitali. Hosted as part of AAMAS, CLaRAMAS brought together researchers working at the intersection of causal learning, causal reasoning, autonomous agents, and multi-agent systems. The workshop aimed […]
Does Germany need its own AI Safety Institute?.
The release of ClaudeMythos, where the UK’s AI Security Institute was the only government body outside the US involved, has given this question new urgency. A detailed concept for a German AI Safety Institute (DAISI) already exists and Tagesspiegel Background has now picked it up. Developed by Kristian Kersting, Kevin Baum and Patrick Schramowski (DFKI), […]
Social Media Campaigns
Work with us
Selected Partners
