Advances in Anomaly Detection and System Reliability

The field is moving towards developing more sophisticated methods for detecting anomalies and improving system reliability. Researchers are exploring new approaches to identify potential threats and failures in complex systems, such as multi-processor system-on-chips and cloud infrastructure. The use of machine learning and data-driven techniques is becoming increasingly popular in this area. Notably, innovative methods for real-time anomaly detection and memory failure prediction are being proposed, which have the potential to significantly improve system reliability and performance. Some noteworthy papers in this area include: M$^2$-MFP, which proposes a multi-scale and multi-level memory failure prediction framework that outperforms existing state-of-the-art methods. Real-Time Decorrelation-Based Anomaly Detection for Multivariate Time Series, which introduces a novel real-time decorrelation-based anomaly detection method that achieves superior performance across diverse anomaly types.

Sources

iThermTroj: Exploiting Intermittent Thermal Trojans in Multi-Processor System-on-Chips

Multi-Queue SSD I/O Modeling & Its Implications for Data Structure Design

M$^2$-MFP: A Multi-Scale and Multi-Level Memory Failure Prediction Framework for Reliable Cloud Infrastructure

Real-Time Decorrelation-Based Anomaly Detection for Multivariate Time Series

Adaptive Gaussian Mixture Models-based Anomaly Detection for under-constrained Cable-Driven Parallel Robots

Built with on top of