Marketing № 1 (2026)
INTELLIGENT INTRUSION DETECTION: LEVERAGING REINFORCEMENT LEARNING FOR ECONOMIC SECURITY AGAINST
DDOS THREATS, Bekov Sanjar Nigmandjanovich
Аннотация
Distributed Denial -of-Service (DDoS) attacks are a persistent threat to digital services and pose a substantial risk to economic stability. This risk is especially notable within financial systems. Conventional intrusion detection systems rely on static ru les or supervised learning models. Both struggle to adapt to rapidly evolving attack strategies. This paper examines the use of reinforcement learning (RL) for intelligent intrusion detection. It emphasizes RL's ability to enable adaptive, real -time decisi ons in adversarial environments. By viewing intrusion detection as a series of decisions, RL-based systems learn optimal mitigation strategies. They do this through ongoing interaction with network environments and feedback -driven reward mechanisms. The analysis brings together recent empirical studies and experimental findings. It shows that RL -based intrusion detection systems achieve high detection accuracy, faster response times, and greater resilience to evolving DDoS threats. These results suggest that RL not only improves technical detection but also boosts economic security. RL minimizes service downtime, reduces operational losses, and supports the provision of continuous digital financial services.
reinforcement LearningIntrusion Detection SystemsDDoS AttacksEconomic SecurityFinancial CybersecurityAdaptive DefenseDigital Services Resilienceобучение с подкреплениемсистемы обнаружения вторженийDDoS -атаки
Источник метаданных: OAI-PMH архив журнала · Sindex не хранит полный текст, а даёт ссылку на источник.