No abstract

This paper provides a comprehensive overview of the applications of game theory in deep learning. Today, deep learning is a fast-evolving area for research in the domain of artificial intelligence. Alternatively, game theory has been showing its multi-dimensional applications in the last few decades. The application of game theory to deep learning includes another dimension in research. Game theory helps to model or solve various deep learning-based problems. Existing research contributions demonstrate that game theory is a potential approach to improve results in deep learning models. The design of deep learning models often involves a game-theoretic approach. Most of the classification problems which popularly employ a deep learning approach can be seen as a Stackelberg game. Generative Adversarial Network (GAN) is a deep learning architecture that has gained popularity in solving complex computer vision problems. GANs have their roots in game theory. The training of the generators and discriminators in GANs is essentially a two-player zero-sum game that allows the model to learn complex functions. This paper will give researchers an extensive account of significant contributions which have taken place in deep learning using game-theoretic concepts thus, giving a clear insight, challenges, and future directions. The current study also details various real-time applications of existing literature, valuable datasets in the field, and the popularity of this research area in recent years of publications and citations.

No abstract

Purpose Any computing architecture cannot be designed with complete confidentiality. As a result, at any point, it may leak the information. So, it is important to decide leakage threshold in any computing architecture. To prevent leakage more than the predefined threshold, quantitative analysis is helpful. This paper aims to provide a method to quantify information leakage in service-oriented architecture (SOA)-based Web services. Design/methodology/approach To visualize the dynamic binding of SOA components, first, the orchestration of components is modeled. The modeling helps to information-theoretically quantify information leakage in SOA-based Web services. Then, the paper considers the non-interference policy in a global way to quantify information leakage. It considers not only variables which interfere with security sensitive content but also other architectural parameters to quantify leakage in Web services. To illustrate the attacker’s ability, a strong threat model has been proposed in the paper. Findings The paper finds that information leakage can be quantified in SOA-based Web services by considering parameters that interfere with security sensitive content and information theory. A hypothetical case study scenario of flight ticket booking Web services has been considered in the present paper in which leakage of 18.89 per cent information is calculated. Originality/value The paper shows that it is practically possible to quantify information leakage in SOA-based Web services. While modeling the SOA-based Web services, it will be of help to architects to identify parameters which may cause the leakage of secret contents.

No abstract