زلیخا رحمانیان

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.