ABSTRACT
Cloud-edge computing is essential for effective data processing, integrating the centralized capabilities of the cloud with the localized advantages of the edge to enhance scalability and responsiveness. Nonetheless, increasing cyberattacks target weaknesses in data management, requiring creative strategies to guarantee strong privacy without compromising performance.The objective of this study is to present an AI-enhanced framework that integrates Rule-Based Intrusion Detection Systems (IDS), the Cuckoo Search Algorithm, Deep Packet Inspection (DPI), and Gaussian Mixture Models (GMM). It seeks to effectively identify, address, and avert data breaches, offering scalable and robust privacy solutions in cloud-edge settings.Rule-Based Intrusion Detection Systems identify predetermined risks, constituting the fundamental layer. The Cuckoo Search Algorithm enhances detection efficacy. DPI provides comprehensive traffic analysis for immediate anomaly discovery. GMM integrates probabilistic modeling to forecast future risks, hence augmenting total system reliability and efficacy.Empirical findings indicate a detection accuracy of 97.8%, surpassing conventional methods in both precision and speed. The hybrid framework's amalgamation of methodologies guarantees scalability, robustness, and flexibility to emerging risks, underscoring its excellence in tackling data privacy issues within cloud-edge ecosystems.The integration provides a dependable, scalable, and efficient framework to enhance data privacy and security in cloud-edge ecosystems, establishing a basis for secure and resilient computing infrastructures to effectively address contemporary cybersecurity concerns.
