امیر جلالی بیدگلی

Online reviews are crucial in influencing consumer decisions and business practices. However, some individuals exploit this system by posting fake reviews, known as spam opinions, to manipulate perceptions. Spam detection systems face significant challenges in robustness due to their primary focus on identifying spam attacks without accounting for adversaries that target the detection mechanisms. This oversight enables spammers to exploit vulnerabilities in traditional algorithms with complex deceptive strategies, ultimately undermining their effectiveness. This paper proposes a novel multi-layer graph-based method that represents reviews, reviewers, and products as interconnected nodes. This approach captures the complex relationships among them and addresses adversarial attempts to manipulate the detection process. Our approach utilizes three key nodes—opinion, reviewer, and product—to assess the honesty, trust, and reliability of reviews, reviewers, and products in the context of potential deception. Furthermore, we develop a simulation tool capable of generating diverse attack scenarios, including those targeting the detection system itself, enabling a comprehensive evaluation of robustness. We compared the performance of our method with other graph-based techniques through simulations and case studies, demonstrating that our method is a competitive solution among existing alternatives.

In every country, airports are among the most important air transport systems in that country. When an aircraft flies from one airport to another, it creates a graph that can be completed with information about each flight, such as the number of flights per path, the number of passengers, traffic load, and so on. In the present paper, the airports of Iran and the domestic flights are considered as a network and the structure of the network is analyzed, and then the measures of complex networks such as degree distribution, shortest path length, analysis of centralities, clustering coefficient and their correlation and the way these centralities behave are examined. This analysis shows the Iranian Airport Network (IAN) that has a degree distribution described by the power function. The average path length in this network is 1.9, and the average clustering coefficient is 0.69, which meets the characteristics of a small-world network and is also considered an example of a disassortative network. The purpose of this research is to investigate the network of airports in Iran, which is ultimately important for the expansion of airports, and also to identify the important points of airports.