Intelligent Anomaly Detection
Integrating AI for real-time monitoring and advanced anomaly detection across diverse system environments.
Anomaly Detection
Developing AI-based model for intelligent anomaly detection and analysis.
AnomalyNet Model
This research will advance our understanding of OpenAI models in several aspects: First, it provides a new perspective on AI systems' potential in anomaly behavior detection, exploring large language models' capabilities in handling system behavior analysis. Second, the AnomalyNet model will demonstrate how to combine behavior analysis with AI technologies, providing a reference framework for similar applications. Third, the research will reveal AI systems' performance characteristics in anomaly detection and behavior prediction. From a societal impact perspective, improved anomaly detection systems will enhance system security levels, protect critical infrastructure, and provide better security guarantees for digital systems.
Deep Learning
My past research has focused on innovative applications of AI anomaly behavior detection systems. In "Intelligent System Anomaly Detection" (published in IEEE Transactions on Dependable and Secure Computing 2022), I proposed a fundamental framework for intelligent anomaly detection. Another work, "AI-driven Behavior Analysis" (USENIX Security 2022), explored AI technology applications in behavior analysis. I also led research on "Real-time Anomaly Pattern Recognition" (AAAI 2023), which developed an innovative real-time anomaly pattern recognition method. The recent "System Behavior Analysis with Large Language Models" (NDSS 2023) systematically analyzed the application prospects of large language models in anomaly behavior detection.