Journal of Engineering Research and Reports

The integration of the Internet of Things (IoT) with artificial intelligence (AI) is transforming home appliances into smarter, more responsive tools that enhance daily living. However, this technological fusion introduces significant security challenges, necessitating a careful balance between security and performance within IoT networks. First, the study answers the question of the trade-offs between security measures and performance metrics in web applications for AI-driven home appliances, and second, how can these trade-offs be optimized to ensure both robust security and high system performance? Using qualitative content analysis, the study identified key security flaws in web application architectures, while quantitative analysis assessed the impact of security protocols on system performance metrics such as latency, throughput, and CPU usage. Atlas.ti and Cisco’s Packet Tracer were utilized for thematic coding and network simulation, respectively, and multivariate regression analysis quantified the influences of security protocols. The results revealed that enhanced security protocols, such as encryption and authentication, significantly impact performance, with encryption increasing latency by an average of 50 milliseconds and reducing throughput by 10% under peak loads. Additionally, CPU usage increased by up to 75% in high-threat scenarios. The proposed security-performance optimization framework dynamically adjusts security measures based on current threat assessments and operational demands, aiming to sustain high performance while ensuring robust security. These findings have real-world applications in the design and implementation of AI-driven home appliances, offering a roadmap for manufacturers to enhance device security without compromising performance. By adopting adaptive security measures and leveraging edge computing, the framework can improve user satisfaction and trust in smart home technologies.