6 links tagged with all of: machine-learning + anomaly-detection
Click any tag below to further narrow down your results
Links
This article discusses how AI technologies are reshaping data quality processes in modern enterprises. It explains the shift from traditional rule-based systems to AI-driven frameworks that enhance data accuracy, automate cleaning, and create trust scores based on data reliability. The use of deep learning, generative models, and reinforcement learning plays a key role in adapting to complex data environments.
This article introduces CoLog, a framework designed to detect both point and collective anomalies in operating system logs using collaborative transformers. It effectively handles different log modalities and has demonstrated high precision and recall across multiple benchmark datasets.
FACADE is a deep-learning-based anomaly detection system created by Google, aimed at enhancing enterprise security by identifying insider threats and account compromises. The GitHub repository provides a reference implementation of the concepts discussed at BlackHat 2025, along with synthetic sample data for training models. It is released on a best-effort basis, allowing users to adapt the code for their needs.
DoorDash has developed an anomaly detection platform to proactively identify emerging fraud trends within their delivery system. By analyzing millions of user segments and employing metrics and dimensions, the platform can surface potential fraud patterns before they escalate into significant losses. The system aims to enhance fraud detection efficiency and supports ongoing expansion to cover more business applications.
The article discusses how Slack developed its anomaly event response system to effectively identify and handle unusual patterns of activity within its platform. It emphasizes the importance of data analysis and machine learning in maintaining platform security and ensuring a smooth user experience. The implementation of this system aims to proactively address potential issues before they escalate.
Qriton's hopfield-anomaly package provides a production-ready Hopfield Neural Network designed for real-time anomaly detection with features like adaptive thresholds and energy-based scoring. The package supports various configurations for tuning detection to specific domains and includes performance profiling tools. It is suitable for diverse use cases, including IoT monitoring, network security, and financial data analysis.