New Kaspersky Machine Learning for Anomaly Detection Predicts Breakdown of Production Processes
New Kaspersky Machine Learning for Anomaly Detection Predicts Breakdown of Production Processes
May 19, 2021
![](https://eu-images.contentstack.com/v3/assets/blt6d90778a997de1cd/blt850556f866500627/654a5a8e05eb4d040a046894/325351_DR23_Graphics_General_Large_Text_v1.png?width=1280&auto=webp&quality=95&format=jpg&disable=upscale)
PRESS RELEASE
Woburn, MA – May 18, 2021 — Today Kaspersky announces that Kaspersky Machine Learning for Anomaly Detection (MLAD), designed to reveal deviations in production processes at the earliest stage, is now generally available as a commercial product. The detector is empowered with ML algorithms that analyze telemetry from machinery sensors. It warns of machine malfunctions by raising alerts as soon as manufacturing process parameters (tags) begin to behave in an unexpected way. Kaspersky MLAD provides a feature-rich graphical interface for detailed analysis of anomalies as well as tools that can integrate the product with existing systems to deliver alerts to operators’ dashboards.
In industrial settings, it is critical to keep technological processes on an optimal path and avoid interruptions such as equipment malfunctions, operator errors, or cyberattacks on industrial control systems. If something goes wrong, early detection can prevent disruption and therefore reduce the cost of downtime, the waste of raw materials and the impact of other serious consequences. According to Kaspersky estimates, a 50% reduction in downtime enables annual savings of up to $1 million for a large power plant or $2.5 million for an oil refinery.1
Kaspersky Machine Learning for Anomaly Detection’s neural network analyzes telemetry in real-time from various sensors used in the production process. It detects minor deviations such as a change in signals’ dynamics or correlations, and gives alerts before the values reach their thresholds and impact performance allowing plant operators to take preventive actions. To be able to detect anomalies, the neural network learns the normal behavior of the machine from historical telemetry data. If a parameter of the production process changes (for example, a new type of raw material is introduced) or a part of the machine is replaced, an operator can re-run the ML trainer to update the neural network. In addition to an ML-based detector, customized diagnostic rules for specific cases can be added at the customer’s request.
Kaspersky MLAD works in the existing plant’s infrastructure and does not require the installation of additional sensors. To obtain data and report the anomalies, Kaspersky MLAD connects to industrial control systems such as SCADA. Alternatively, it can be integrated with Kaspersky Industrial CyberSecurity for Networks. The product natively supports popular protocols including OPC UA, MQTT, AMQP, as well as REST, which makes it applicable to systems with diverse equipment.
Kaspersky MLAD provides a graphical interface for the analysis of detected anomalies. Thanks to the visualized time plots of all monitored processes, an expert can see what went wrong, when, and in what part of the system.
“Advanced ML algorithms and the ability to adapt to particular industrial processes make Kaspersky Machine Learning for Anomaly Detection an essential tool to ensure smooth production,” comments Andrey Lavrentyev, head of technology research department at Kaspersky. “It complements monitoring systems and machine operators’ expertise with the ability to detect anomalies in a complex environment. No matter what causes the deviations, the downtime, equipment breakdowns and disasters can be prevented thanks to early alerts. We have been developing the technology for several years and today we’re happy to announce the general availability of the fully-fledged product to help customers achieve these benefits.”
For more information about Kaspersky Machine Learning for Anomaly Detection, please visit https://mlad.kaspersky.com/.
1 The estimation is based on Kaspersky analysis of different parameters such as duration of downtimes, parameters of economic activity of organizations, and modeling.
You May Also Like
Catch the Threat Before it Catches you: Proactive Ransomware Defense
September 5, 2024How to Evaluate Hybrid-Cloud Network Policies and Enhance Security
September 18, 2024DORA and PCI DSS 4.0: Scale Your Mainframe Security Strategy Among Evolving Regulations
September 26, 2024Harnessing the Power of Automation to Boost Enterprise Cybersecurity
October 3, 2024
[Virtual Event] The Essential Guide to Cloud Management
October 17, 2024Black Hat Europe - December 9-12 - Learn More
December 10, 2024SecTor - Canada's IT Security Conference Oct 22-24 - Learn More
October 22, 2024