News

Secure AI for Health Defense, and Beyond that took place at UC San Diego, on February 19, 2025

Exchange on cybersecurity from AI to satellite research

On January 24, 2025, Professor of Informatics Ahmad-Reza Sadeghi welcomed the U.S. Consul General in Frankfurt, Brian Heath, and his delegation for a visit to the System Security Lab. The discussions focused on current developments in IT security, ranging from artificial intelligence (AI) to satellite research.

The Frankfurter Allgemeine Zeitung has featured the groundbreaking work of Prof. Ahmad-Reza Sadeghi and our System Security Lab at TU Darmstadt. The article explores how we are enhancing the security of smart technologies and IoT devices, ranging from connected household appliances to advanced learning systems.

The System Security Lab from TU Darmstadt, in collaboration with CROSSING, have hosted the fourth annual High-Tech Women Event (HTW’24) in Darmstadt on September 25-26, 2024 . Organized since 2020, this event brought together accomplished women in technology and science from around the world.

On September 24, 2024, at Jagdschloss Kranichstein in Darmstadt, Germany, a memorial event will honor Professor Ross Anderson from the University of Cambridge, renowned for his pioneering contributions to computer security and cryptography. His work profoundly influenced modern security practices, and his legacy as a mentor and advocate for digital rights will be celebrated.

Last week, members of our research group — Alessandro Pegoraro, Phillip Rieger, and Prof. Dr.-Ing. Ahmad-Reza Sadeghi — presented a comprehensive tutorial on the security and privacy of AI-based systems at the prestigious summer school on real-world cryptography and privacy in Vodice, Croatia. This event attracted researchers from around the globe, who shared their insights on various security and privacy topics.

Last week, our group participated in the prestigious IEEE Symposium on Security and Privacy and presented 3 of our newest research papers there.

On February 15, 2024, Phillip Rieger and Alessandro Pegoraro from our group organized the AI Coding Challenge focused on the security and privacy aspects of Federated Learning (FL). The event was organized in collaboration with Platform Lernende Systeme and IBM Innovation Studios. Federated Learning represents a decentralized approach to machine learning, allowing multiple clients to collectively train Deep Neural Networks (DNNs) without centralizing data. This method ensures data privacy by having each client train DNNs on their local datasets and share only the DNN parameters. Despite its benefits, this decentralization also opens the door to potential security threats, including the submission of manipulated DNN models by malicious clients.

Shaping the Future of Digital Trust