Masao Kubo

When a landslide occurs, the person who discovers it will likely report the disaster; however, a person who receives this report will likely need someone on site to check, since the reporter may have misread the information. This allows third parties to make use of the confirmed information. Facilitating such mechanisms for reporting, confirming, and utilizing disaster information is considered to be necessary for sharing details about one. In this paper, we proposed and analyzed an agent-based model that incorporates disaster behavior into the model of Toriumi et al. The reporting of a disaster refers to submitting articles, the confirmation of the information by another person refers to commenting on the articles, and utilizing the information refers to comments responding to the aforementioned comment using the framework of meta-reward games, based on the prisoner’s dilemma game. We then analyze the costs and rewards to encourage cooperation in several social networks. It is found that reducing the cost of commenting (conforming) encourages the submission of information. The properties of the results do not depend on network structure, which is novel and unexpected, and it is expected that the properties of real social networks will be predictable.

As online resources such as social media are increasingly used in disaster situations, confusion caused by the spread of false information, misinformation, and hoaxes has become an issue. Although a large amount of research has been conducted on how to suppress disinformation, i.e., the widespread dissemination of such false information, most of the research from a revenue perspective has been based on prisoner’s dilemma experiments, and there has been no analysis of measures to deal with the actual occurrence of disinformation on disaster SNSs. In this paper, we focus on the fact that one of the characteristics of disaster SNS information is that it allows citizens to confirm the reality of a disaster. Hereafter, we refer to this as collective debunking, and we propose a profit-agent model for it and conduct an analysis using an evolutionary game. As a result, we experimentally found that deception in the confirmation of disaster information uploaded to SNS is likely to lead to the occurrence of disinformation. We also found that if this deception can be detected and punished, for example by patrols, it tends to suppress the occurrence of disinformation.

Title: Consensus Building in Box-Pushing Problem by BRT Agent that Votes with Frequency Proportional to Profit | Keywords: collective intelligence, swarm intelligence, voting model, reinforcement learning | Author: Masao Kubo, Hiroshi Sato, and Akihiro Yamaguchi

Malware is becoming an effective support tool not only for professional hackers but also for amateur ones. Due to the support of free malware generators, anyone can easily create various types of malicious code. The increasing amount of novel malware is a daily global problem. Current machine learning-based methods, especially image-based malware classification approaches, are attracting significant attention because of their accuracy and computational cost. Convolutional Neural Networks are widely applied in malware classification; however, CNN needs a deep architecture and GPUs for parallel processing to achieve high performance. By contrast, a simple model merely contained a Multilayer Perceptron called MLP-mixer with fewer hyperparameters that can run in various environments without GPUs and is not too far behind CNN in terms of performance. In this study, we try applying an Autoencoder (AE) to improve the performance of the MLP-mixer. AE is widely used in several applications as dimensionality reduction to filter out the noise and identify crucial elements of the input data. Taking this advantage from AE, we propose a lightweight ensemble architecture by combining a customizer MLP-mixer and Autoencoder to refine features extracted from the MLP-mixer with the encoder-decoder architecture of the autoencoder. We achieve overperformance through various experiments compared to other cutting-edge techniques using Malimg and Malheur datasets which contain 9939 (25 malware families) and 3133 variant samples (24 malware families).