Trustworthy AI Development Guidelines for Human System Interaction

Artificial Intelligence (AI) is influencing almost all areas of human life. Even though these AI-based systems frequently provide state-of-the-art performance, humans still hesitate to develop, deploy, and use AI systems. The main reason for this is the lack of trust in AI systems caused by the deficiency of transparency of existing AI systems. As a solution, “Trustworthy AI” research area merged with the goal of defining guidelines and frameworks for improving user trust in AI systems, allowing humans to use them without fear. While trust in AI is an active area of research, very little work exists where the focus is to build human trust to improve the interactions between human and AI systems. In this paper, we provide a concise survey on concepts of trustworthy AI. Further, we present trustworthy AI development guidelines for improving the user trust to enhance the interactions between AI systems and humans, that happen during the AI system life cycle.

[1]  L. Floridi,et al.  Data ethics , 2021, Effective Directors.

[2]  Daniel L. Marino,et al.  AI Augmentation for Trustworthy AI: Augmented Robot Teleoperation , 2020, 2020 13th International Conference on Human System Interaction (HSI).

[3]  Nathalie A. Smuha.  The EU Approach to Ethics Guidelines for Trustworthy Artificial Intelligence , 2019, Computer Law Review International.

[4]  Krzysztof Czuszyński,et al.  Gesture Recognition With the Linear Optical Sensor and Recurrent Neural Networks , 2018, IEEE Sensors Journal.

[5]  Kasun Amarasinghe,et al.  Explaining What a Neural Network has Learned: Toward Transparent Classification , 2019, 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[6]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[7]  Daniel L. Marino,et al.  Cyber and Physical Anomaly Detection in Smart-Grids , 2019, 2019 Resilience Week (RWS).

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Daniel L. Marino,et al.  Generalization of Deep Learning for Cyber-Physical System Security: A Survey , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.

[10]  Daniel L. Marino,et al.  Combining Physics-Based Domain Knowledge and Machine Learning using Variational Gaussian Processes with Explicit Linear Prior , 2019, ArXiv.

[11]  Kwasniewska,et al.  Improving Accuracy of Contactless Respiratory Rate Estimation by Enhancing Thermal Sequences with Deep Neural Networks , 2019, Applied Sciences.

[12]  Milos Manic,et al.  Toward Explainable Deep Neural Network Based Anomaly Detection , 2018, 2018 11th International Conference on Human System Interaction (HSI).

[13]  Karen Yeung,et al.  Recommendation of the Council on Artificial Intelligence (OECD) , 2020, International Legal Materials.

[14]  Daniel L. Marino,et al.  Data-driven Stochastic Anomaly Detection on Smart-Grid communications using Mixture Poisson Distributions , 2019, IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society.

[15]  Daniel L. Marino,et al.  An Adversarial Approach for Explainable AI in Intrusion Detection Systems , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.

[16]  Chathurika S. Wickramasinghe,et al.  Deep Self-Organizing Maps for Unsupervised Image Classification , 2019, IEEE Transactions on Industrial Informatics.

[17]  Milos Manic,et al.  Data driven decision support for reliable biomass feedstock preprocessing , 2017, 2017 Resilience Week (RWS).

[18]  Daniel L. Marino,et al.  Modeling and Planning Under Uncertainty Using Deep Neural Networks , 2019, IEEE Transactions on Industrial Informatics.