Architectural Patterns for Integrating AI Technology into Safety-Critical Systems

Artificial Intelligence (AI) is widely acknowledged as one of the most disruptive technologies driving the digital transformation of industries, enterprises, and societies in the 21st century. Advances in computing speed, algorithmic improvements, and access to a vast amount of data contributed to the adaption of AI in many different domains. Due to the outstanding performance, AI technology is increasingly integrated into safety-critical applications. However, the established safety engineering processes and practices have been only successfully applied in conventional model-based system development and no commonly agreed approaches for integrating AI technology are available yet. This work presents two architectural patterns that can support designers and engineers in the conception of safety-critical AI-enhanced cyber-physical system (CPS) applications. The first pattern addresses the problem of integrating AI capabilities into safety-critical functions. The second pattern deals with architectural approaches to integrate AI technologies for monitoring and learning system-specific behavior at runtime.

[1]  Tzi-cker Chiueh,et al.  Towards Automatic Learning of Valid Services for Honeypots , 2004, ICDCIT.

[2]  Radu State,et al.  Adaptive and self-configurable honeypots , 2011, 12th IFIP/IEEE International Symposium on Integrated Network Management (IM 2011) and Workshops.

[3]  Michael Desmond,et al.  Towards Automating the AI Operations Lifecycle , 2020, ArXiv.

[4]  D. Ashok Kumar,et al.  INTRUSION DETECTION SYSTEMS: A REVIEW , 2017 .

[5]  G. F. Malykhina,et al.  Digital Twin Technology As A Basis Of The Industry In Future , 2018 .

[6]  Georg Macher,et al.  Towards Cyber-Physical Infrastructure as-a-Service (CPIaaS) in the Era of Industry 4.0 , 2019, EuroSPI.

[7]  Christopher Preschern.  Pattern-Based Development of Embedded Systems for Safety and Security , 2014 .

[8]  L. Spitzner,et al.  Honeypots: Tracking Hackers , 2002 .

[9]  Moussa Boukhnifer,et al.  Artificial Intelligence for Vehicle Behavior Anticipation: Hybrid Approach Based on Maneuver Classification and Trajectory Prediction , 2020, IEEE Access.

[10]  Anit Kumar Sahu,et al.  Federated Learning: Challenges, Methods, and Future Directions , 2019, IEEE Signal Processing Magazine.

[11]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[12]  Hendra Kesuma,et al.  Artificial Intelligence Implementation on Voice Command and Sensor Anomaly Detection for Enhancing Human Habitation in Space Mission , 2019, 2019 9th International Conference on Recent Advances in Space Technologies (RAST).

[13]  Rolf Steinhilper,et al.  The Digital Twin: Demonstrating the Potential of Real Time Data Acquisition in Production Systems ☆ , 2017 .

[14]  Eduardo Tovar,et al.  How realistic is the mixed-criticality real-time system model? , 2015, RTNS.

[15]  Davide Bacciu,et al.  Federated Reservoir Computing Neural Networks , 2021, 2021 International Joint Conference on Neural Networks (IJCNN).

[16]  Wira Zanoramy Ansiry Zakaria,et al.  A review on artificial intelligence techniques for developing intelligent honeypot , 2012, 2012 8th International Conference on Computing Technology and Information Management (NCM and ICNIT).

[17]  G. Macher,et al.  Cybersecurity Threat Analysis, Risk Assessment and Design Patterns for Automotive Networked Embedded Systems: A Case Study , 2021, J. Univers. Comput. Sci..

[18]  Christian Kreiner,et al.  An architectural approach to the integration of safety and security requirements in smart products and systems design , 2018 .

[19]  Mario Hirz,et al.  Sensor and object recognition technologies for self-driving cars , 2017 .

[20]  Carl S. Byington,et al.  Selected Artificial Intelligence Methods Applied within an Integrated Vehicle Health Management System , 2007, AAAI Fall Symposium: Artificial Intelligence for Prognostics.