14.08.2026
Stephan Günnemann Featured in t3n on Data Poisoning and AI Security
Understanding the Growing Threat of Manipulated Data
MCML PI Stephan Günnemann is featured in a recent t3n article examining data poisoning as a growing threat to the security and reliability of AI systems. Data poisoning involves deliberately manipulating data to influence how AI models behave, potentially causing them to produce misleading or harmful results.
Günnemann highlights the broader implications of data poisoning, including its potential use to pursue political influence or economic advantages. The article explores how manipulated data can affect AI-powered systems such as recommendation services and why detecting such attacks remains a significant challenge.
Related
29.10.2026
Teaching Language Models to Express Uncertainty
An ICLR 2026 paper shows how reinforcement learning improves confidence estimates from language models.
27.10.2026
Runner-Up Prize at AutoML 2026 for Tabular-DC-Bench
Tabular-DC-Bench, by MCML Junior Member Mamdouh Aljoud and MCML Director Thomas Seidl, among others, won a runner-up prize at AutoML 2026.
27.10.2026
Welcoming Ewa Szczurek to MCML
Ewa Szczurek joins MCML as Professor of AI in Life Sciences at LMU, focusing on probabilistic and generative models for medicine.
