Gurucul UEBA vs VbtEngine UEBA
Gurucul UEBA
gurucul.comVbtEngine UEBA
vbtengine.comSide by side
| Figure | Gurucul UEBA | VbtEngine UEBA |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 0 |
| Spec score · User and Entity Behavior Analytics Software | 7.3 (#11) | 6.8 (#15) |
| Deployment | Gurucul describes platform deployment options including on-premises, hybrid, SaaS, private cloud, GovCloud, and multi-cloud. | The technical summary lists deployment as on-prem. |
| Detection | Gurucul says UEBA includes more than 5,000 machine learning models and reports 70% fewer false positives. | The engine describes twelve anomaly types, including new source IP, unusual hour, dormant reactivation, suspected account takeover, lateral movement, and suspected brute force. |
| Purpose | UEBA uses machine learning to learn normal user, device, and application behavior and detect unusual activity that may indicate compromise or malicious behavior. | UEBA learns user and entity behavior to surface anomalies and insider-threat signals with a risk score. |
| Risk scoring | The product assigns entities risk prioritization scores from 0 to 100 to help prioritize known and unknown threats. | Certain signals can be correlated so that two individually medium-risk signals escalate into a high-risk finding. |
| Support | The product page links to Gurucul Support and offers a request-a-demo contact path. | Technical support is available on weekdays from 09:00 to 18:00 Istanbul time (GMT+3). |
Plans
In their own words
Gurucul UEBA
Gurucul UEBA is a user and entity behavior analytics product for detecting unusual activity across users, devices, applications, servers, networks and IoT devices. Machine-learning models learn normal behavior and identify activity that may indicate compromise or malicious behavior. Gurucul describes more than 5,000 models and reports 70% fewer false positives. Entities receive risk-prioritization scores from 0 to 100, helping security teams order investigations of known and unknown threats. Link Chain Analysis connects AI-agent, user and entity activity into contextual evidence cases. Listed use cases include insider risk, host and device compromise, lateral movement, data exfiltration, and account or credential compromise. Integrations cover IAM, IGA and PAM sources and SIEMs including Splunk, Microsoft Sentinel and IBM QRadar. Deployment options include self-hosted, web, on-premises, hybrid, SaaS, private cloud, GovCloud and multi-cloud. Pricing is on request.
VbtEngine UEBA
VbtEngine UEBA analyzes user and entity behavior to surface anomalies and insider-threat signals, then assigns risk scores to findings. It uses existing FortiGate VPN and SSH logs from fw_vpn_log and fw_ssh_log, with no new agent required. The engine builds a 30-day behavioral baseline while excluding the latest 24 hours, and describes twelve anomaly types, including new users or source IPs, unusual hours, volume spikes, suspected account takeover, lateral movement, and suspected brute force. Related signals can be correlated so that two individually medium-risk signals may become a high-risk finding. Location filtering excludes internal, VPN, loopback, link-local, multicast, and CGNAT addresses; two IPs in the same /24 are not treated as different locations. Heavy scans run in a background worker while the main API reads a cache. Data, deduplication, and seven-day anomaly history are kept separate by tenant. Sequence correlation can automatically open a SIEM case after a brute-force lockout followed within an hour by specified anomalies. The technical summary specifies on-prem deployment.