- +44 7576 444493
- info@gensechub.com
Enhances analyst’s investigation capabilities through a Smart User Activity Timeline, in which activities of each user are arranged chronologically. This enables analysts to gain real-time insights into any suspicious activity at the very beginning stage, before it affects the entire infrastructure
Monitors logs in real-time, alerting on anomalous user behavior. Each model undergoes training to establish a baseline. If any deviations are detected, UEBA alerts and reports contextual information
Utilizes diverse machine learning modules: Reinforcement Learning, Deep Learning, Supervised Machine Learning, Bayesian Networks, and other models based on time, category, continuity, and discrete aspects
Facilitates forensics search in both RAW and Parsed data using intuitive GUI with natural language support. The system ensures user-friendly experience, offering compatible options and auto-suggestions for selected fields based on contextual data
Provides user-friendly visualizations, offering insights into the organization’s security posture. Alerts for a specific tenant/group can be viewed separately. Dashboards are configurable for real-time or historical data viewing
Provides out-of-the-box threat detection for various malicious activities, including Lateral Movement, Data Exfiltration, Anomalous Data Access, Brute Force detection, Insider Threat detection, and Network Behavioral-based detections. Proactively monitors privilege misuse activities
High accuracy machine identification, even if IP addresses change
Fine-tuning of metadata attributes for behaviour models
Granular role-based access control (RBAC)
Dedicated report generation engine with built-in templates for exporting reports in PDF, CSV, and Excel formats
One-click export of raw log data
Automatic report generation through scheduling
Alert mechanism for threat detection
Web-based application for easy access
Integration with enterprise authentication systems
Supports creation of custom models and rules/policies that can be automatically adjusted through automated learning
Auto identification of trusted hosts and compromised entities
Self-learning behavioural analysis to dynamically model each device
Optimizable risk models for better threat detection
Retraining of the model based on feedback from security analytics
Auto identification and classification of users and entities
Flexibility to configure rolling window of period for behaviour profiling
Support for high availability (HA) architecture
Competency in deeper detection, identification & insights, at it’s best