Cognitive Security

With the rapid development of digital innovation, we are moving toward an era of interconnection and automation with the focus on technologies such as the Internet of Things, big data, machine learning, etc. Corporations, organizations and people are revolutionizing production, processes and work environments. Trends like Industry 4.0, artificial intelligence and IoT offer enormous benefits for efficiency and connectivity, but they also impose bigger challenges on cybersecurity.

Data volume and complexity are currently scaling up incredibly fast. Security engineers are overwhelmed by the need to handle an exponentially rising number of cyber threats, and it is becoming much easier for attackers to carry out malicious actions on their targets using a vast number of publicly available hacking tools. It is therefore essential to develop innovative security technologies that can help us better understand potential threats and malicious behavior, and to provide more secure and robust protection mechanisms.

Expertise

Fraunhofer AISEC develops innovative technologies for cognitive security, in which we leverage cutting-edge machine learning algorithms to enhance current IT systems with regard to both software and hardware security. Using techniques like machine learning and deep neural networks, these cybersecurity systems can be enhanced to dynamically adapt to environmental changes. Security engineers can also enhance their ability to handle large-scale and high-complexity cyberattacks. We design and develop cognitive security solutions for the prediction, understanding and deduction of malicious activities, and we provide protection mechanisms as well as best practice. We also collaborate with other security technology teams to provide customisied solutions matching specific customer requirements.

Skills and services at a glance

  • Concept and Prototype for large scale real-time anomaly detection systems, e.g., network-based intrusion detection system.
  • Pentesting and hardening for AI-based security products, such as intrusion detection systems, face recognition cameras.
  • Concept and Prototype for User-Entity Behavior Analysis
  • Concept for next generation Cyber Threat Intelligence Platform
  • Concept for next generation Security Information Event Management
  • Seminar and Training courses on Machine Learning for Cybersecurity

Publications

  • K. Böttinger, G. Hansch, and B. Filipovic. “Detecting and Correlating Supranational Threats for Critical Infrastructures”. In 15th European Conference on Cyber Warfare and Security (ECCWS 2016), 2016.
  • K. Böttinger, D. Schuster, and C. Eckert. “Detecting Fingerprinted Data in {TLS} Traffic”. In Proceedings of the 10th ACM Symposium on Information, Computer and Communications Security, 2015, pp. 633–638.
  • H. Xiao, B. Biggio, G. Brown, G. Fumera, C. Eckert, and F. Roli. “Is Feature Selection Secure against Training Data Poisoning ?”. Int’l Conf. Mach. Learn., vol. 37, 2015.
  • D. Schuster and R. Hesselbarth. “Evaluation of Bistable Ring PUFs Using Single Layer Neural Networks”. In Trust and Trustworthy Computing, Springer, 2014, pp. 101–109.
  • H. Xiao, B. Biggio, B. Nelson, H. Xiao, C. Eckert, and F. Roli. “Support Vector Machines under Adversarial Label Contamination”. J. Neurocomputing, Spec. Issue Adv. Learn. with Label Noise, Aug. 2014.

  • H. Xiao and C. Eckert. “Lazy Gaussian Process Committee for Real-Time Online Regression”. In 27th AAAI Conference on Artificial Intelligence (AAAI ’13), 2013.
  • H. Xiao and C. Eckert. “Efficient Online Sequence Prediction with Side Information”. In IEEE International Conference on Data Mining (ICDM), 2013.
  • H. Xiao and C. Eckert. “Indicative support vector clustering with its application on anomaly detection”. Proc. - 2013 12th Int. Conf. Mach. Learn. Appl. ICMLA 2013, vol. 1, pp. 273–276, 2013.H. Xiao, H. Xiao, and C. Eckert, “OPARS: Objective photo aesthetics ranking system,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 7814 LNCS, pp. 861–864, 2013.
  • H. Xiao, H. Xiao, and C. Eckert. “Learning from multiple observers with unknown expertise”. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 7818 LNAI, no. PART 1, pp. 595–606, 2013.
  • H. Xiao, H. Xiao, and C. Eckert. “Adversarial Label Flips Attack on Support Vector Machines”. In 20th European Conference on Artificial Intelligence (ECAI), 2012.