Send email Copy Email Address

2024-03-12
 

Examining cybersecurity in the era of generative AI

The research project "AIgenCY - Opportunities and risks of generative AI in cybersecurity" has been launched: Leading experts from science and industry are taking on the challenge of researching the implications of generative artificial intelligence (AI) for cybersecurity. CISPA researchers Dr. Lea Schönherr, Prof. Dr. Thorsten Holz and Prof. Dr. Mario Fritz are contributing to the project.

The AIgenCY research project, which is supported by the German Federal Ministry of Education and Research, brings together specialists from the CISPA Helmholtz Center for Information Security, Technische Universität Berlin and Freie Universität Berlin under the leadership of the Fraunhofer Institute for Applied and Integrated Security, AISEC. AIgenCY also cooperates with the pioneering AI company Aleph Alpha from Heidelberg. The project partners aim at analyzing the complex effects that generative AI has on cybersecurity, particularly with regard to national critical infrastructures. 

The fast-paced developments in the field of generative AI, particularly regarding neural networks, are revolutionizing the creation of digital content. Generative AI systems are already able to generate and refine authentic texts, visual content and complex program codes. These capabilities open up new opportunities, but also pose significant risks - especially for the cybersecurity of national critical infrastructures and the cornerstones of our democracy. AIgenCY is dedicated to the task of identifying potential threats from AI-generated content and developing robust defense strategies to consolidate Germany's digital sovereignty and protect critical infrastructures.

As part of the project, an experimental laboratory will be set up to examine the applicability of generative AI technologies in practical scenarios. The research team will focus on the following core issues:

  • Combating malware: analyzing the generation of advanced malware by AI and developing appropriate countermeasures.
  • Preventing social engineering, disinformation and fraudulent campaigns: increasing vigilance and improving the detection of automated attacks.
  • Information collection and processing (reconnaissance): Understanding preventive attack strategies and their defense.
  • Explainability and inference: interpreting the decision making of generative AI models and identifying systemic vulnerabilities.
  • Watermarking and anomaly detection: tracing the origin of data and detecting unusual patterns that indicate possible attacks.

AIgenCY aims to make a significant contribution to the protection of critical infrastructures, strengthen Germany as a location for innovation, deepen expertise in the field of cybersecurity and promote the local economy. The project will make an important contribution to overcoming the social challenges posed by new AI technologies.