Machine manufacturer TRUMPF is collaborating with ASVIN and other partners on the KI Fogger project, which aims to develop a new approach to securing AI systems.
TRUMPF representatives Mirko Ross and Klaus Bauer presented the project at the Hannover Messe trade fair.
“There is no AI system that we cannot force to do what we want.”
As AI spreads rapidly within companies, the risk of competitors distilling AI training data is increasing, which could lead to the loss of important competitive advantages.
KI Fogger offers a new way of securing AI systems.
By obscuring model results, it enables the protection of intellectual property even in the event of model loss. These methods are based on intrinsic model encryption and prevent the unauthorised use of the information contained within.
You can find further details on the Hannover Messe blog.
https://www.hannovermesse.de/en/news/news-articles/-we-can-manipulate-any-ai-
Konrad Buck
Head of Press and Media Relations
Background & Expert Access for Media
- Product & technology insights – technical context, solution architecture, and real-world use cases for professional and trade media
- Expert commentary & background talks – our CEO is available as an expert source on current cybersecurity developments, threat landscapes, and the impact of AI on security and regulation
I speak openly, fact-based, and without PR spin. I am a former IT journalist with decades of experience in the IT and cybersecurity space, familiar with the highs and lows of the industry. Off-the-record discussions are possible upon request.
