中身はほぼ以下の論文紹介です!
Soremekun, E., Papadakis, M., Cordy, M., & Traon, Y. Le. (2022). Software Fairness: An Analysis and Survey. ArXiv. Retrieved from http://arxiv.org/abs/2205.08809
This document discusses some of the challenges in developing AI systems that utilize machine learning. It notes that machine learning systems rely on probabilities and statistics based on training data, making quality assurance difficult. It is also difficult to fully understand and interpret models from deep neural networks. The document suggests that new approaches are needed for developing machine learning-based systems, as traditional software engineering approaches do not work well. Establishing the field of "machine learning engineering" is important for building AI systems that can reliably ensure quality.
WM2SP16 Keynote: Current and Future challenge of Model and Modelling on Secur...Nobukazu Yoshioka
My talk includes current models and modelling on Security and Privacy: Conceptual Models such as SIG, Common Criteria, STIX, SCPM, UML based models such as Misusecase, UMLsec, secureUML, and GORE models such as SecureTropos, i*/Tropos, KAOS etc.
Additionally, research challenges on the Security and Privacy Model and Modelling are discussed.
Operation on Models on Security and Privacy with consistency
Hybrid Models on Security and Privacy
Big data and Machine Learning on Security and Privacy Modelling
Ahmed Elkhodary & Jon Whittle : "A Survey of Approaches to Adaptive Security", International Workshop on Software Engineering for Adaptive and Self-Managing System (SEAMS’07)
This document discusses some of the challenges in developing AI systems that utilize machine learning. It notes that machine learning systems rely on probabilities and statistics based on training data, making quality assurance difficult. It is also difficult to fully understand and interpret models from deep neural networks. The document suggests that new approaches are needed for developing machine learning-based systems, as traditional software engineering approaches do not work well. Establishing the field of "machine learning engineering" is important for building AI systems that can reliably ensure quality.
WM2SP16 Keynote: Current and Future challenge of Model and Modelling on Secur...Nobukazu Yoshioka
My talk includes current models and modelling on Security and Privacy: Conceptual Models such as SIG, Common Criteria, STIX, SCPM, UML based models such as Misusecase, UMLsec, secureUML, and GORE models such as SecureTropos, i*/Tropos, KAOS etc.
Additionally, research challenges on the Security and Privacy Model and Modelling are discussed.
Operation on Models on Security and Privacy with consistency
Hybrid Models on Security and Privacy
Big data and Machine Learning on Security and Privacy Modelling
Ahmed Elkhodary & Jon Whittle : "A Survey of Approaches to Adaptive Security", International Workshop on Software Engineering for Adaptive and Self-Managing System (SEAMS’07)