O.Y. Veprytska, V.S. Kharchenko
Existing artificial intelligence (AI) services provided by cloud providers (Artificial Intelligence as a Service (AIaaS)) and their explainability have been studied. The characteristics and provision of objective evaluation of explainable AI as a service (eXplainable AI as a Service (XAIaaS)) are defined. AIaaS solutions provided by cloud providers Amazon Web Services, Google Cloud Platform and Microsoft Azure were analyzed. Non-functional requirements for XAIaaS evaluation of such systems have been formed. A model has been developed and an example of the quality assessment of an AI system for image detection of weapons has been provided, and an example of its metric assessment has been provided. Directions for further research: parameterization of explainability and its sub-characteristics for services, development of algorithms for determining metrics for evaluating the quality of AI and XAIaaS systems, development of means for ensuring explainability.
explainable artificial intelligence, AI as a Service, requirements for artificial intelligence, model of AI quality, metrics
- Elger, P.P. and Shanaghy E.E. (2020), AI As a Service: Serverless Machine Learning with AWS, Manning Publications Company, available at: https://www.manning.com/books/ai-as-a-service.
- Top 10 artificial intelligence problems you should know, CloudMoyo, Enabling digital transformation with Cloud and AI, available at: https://www.cloudmoyo.com/blog/ai-ml-automation/top-10-potential-ai-artificial-intelligence-problems/ (accessed: July 03, 2022).
- Artificial Intelligence and Life in 2030, Analysis & Policy Observatory, available at: https://apo.org.au/sites/default/files/resource-files/2016-09/apo-nid210721.pdf (accessed: July 04, 2022).
- What Is AIaaS? AI as a Service Explained, BMC Blogs, available at: https://www.bmc. com/blogs/ai-as-a-service-aiaas/ (accessed: July 04, 2022).
- O'Brien, S. (2018), Anything as a Service (XaaS), RingCentral UK Blog, available at: https://www.ringcentral.com/gb/en/blog/definitions/anything-as-a-service-xaas/ (accessed: July 08, 2022).
- Lins, S. et al. (2021), “Artificial Intelligence as a Service”, Business & Information Systems Engineering, Vol. 63, no. 4, pp. 441–456, available at: https://doi.org/10.1007/s12599-021-00708-w
- Adadi, A. and Berrada, M. (2018), “Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)”, IEEE Access, Vol. 6, pp. 52138–52160, available at: https://doi.org/10.1109/ACCESS.2018.2870052
- Kharchenko, V., Fesenko, H. and Illiashenko, O. (2022), “A basic model of non-functional characteristics for assessing the quality of artificial intelligence”, Radioelektronic and Computer Systems, 2, pp. 131–144, available at: https://doi.org/10.32620/reks.2022.2.11 (accessed: July 06, 2022).
- Artificial Intelligence Services, Amazon Web Services, available at: https://aws.amazon.com/ machine-learning/ai-services/ (accessed: July 03, 2022).
- Directory of Azure Cloud Services, Microsoft Azure, Cloud Computing Services, available at: https://azure.microsoft.com/en-us/services/ (accessed: July 03, 2022).
- Products and Services, Google Cloud, available at: https://cloud.google.com/products# section-3 (accessed: July 03, 2022).
- ISO 25010, PORTAL ISO 25000, available at: https://iso25000.com/index.php/en/iso-25000- standards/iso-25010 (accessed: July 04, 2022).
- Kharchenko, V., Fesenko, H. and Illiashenko, O. (2022), “Quality Models for Artificial Intelligence Systems: Characteristic-Based Approach, Development and Application”, Sensors, Vol. 22, no. 13, pp. 4865, available at: https://doi.org/10.3390/s22134865.
- Overview of Everything as a Service (XaaS), GeeksforGeeks, available at: https://www. org/overview-of-everything-as-a-service-xaas/ (accessed: July 04, 2022).
- Saeed, W. (2021), Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities, arXiv.org e-Print archive, available at: https://arxiv.org/pdf/2111. pdf (accessed: July 04, 2022).
- Than, A. (2022), “Interpretable AI: Building explainable machine learning systems”, Manning, available at: https://www.manning.com/books/interpretable-ai.
- AI Gun Detection Technology, ZeroEyes, available at: https://zeroeyes.com/ (accessed: July 11, 2022).
- Ahmed, S. et al. (2022), Development and Optimization of Deep Learning Models for Weapon Detection in Surveillance Videos, Applied Sciences, Vol. 12, no. 12, pp. 5772, available at: https://doi.org/10.3390/app12125772 (accessed: July 11, 2022).
- Google apologizes after its Vision AI produced racist results, AlgorithmWatch, available at: https://algorithmwatch.org/en/google-vision-racism/ (accessed: July 04, 2022).
- Vasyliev I. (2022), “A framework for metricevaluation of artificial intelligence systems based on quality model”, Systemy upravlinnya, navihatsiyi ta zvyazku, Vol. 68, pp. 41–45, available at: https://doi.org/10.26906/SUNZ.2022.2.041 (accessed: July 10, 2022).