TECHNOLOGIE

Moteur AI

Battle Tested, Purpose-built, AI

Go beyond alerts – detect and respond to Incidents. Industry leading Machine Learning (ML) algorithms detect threats in the enterprise. Stellar Cyber’s AI engine is like a team of world class security experts working around the clock at massive scale to make your team faster and more effective.

AI That Résultats

The output of Stellar Cyber’s AI Engine can be simplified down to generating two types of data
for security teams: alerteset incidents. Together,alerts and incidents provide the depth and holistic
view teams need to make rapid decisions

Nouvelles alertes

Alerts are instances of specific suspicious or high risk behavior and are the building blocks of Incidents. Stellar Cyber ships with 200+ Alert Types out of the box; no configuration required. Alert Types are mapped to the Chaîne d'élimination XDR, pour permettre la hiérarchisation et la corrélation. Les alertes individuelles ont une description générée et lisible par l'homme de ce qui s'est passé et des mesures correctives recommandées pour une réponse rapide.
Example alert types include:
  • Anomalie de comportement du scanner externe
  • Attaque par force brute RDP interne
  • Énumération interne du nom d'utilisateur SMB

Incidents automatiquement corrélés

Les incidents sont des ensembles corrélés d'alertes et d'autres données de support, notamment des signaux, des actifs, des utilisateurs et des processus. Les incidents représentent une attaque entière ou une séquence d'actions à haut risque. En temps réel, à mesure que de nouvelles alertes sont générées, les alertes sont attribuées aux incidents pertinents afin que les attaques puissent être détectées et traitées avant leur achèvement. Les incidents dans Stellar Cyber ​​sont modifiables, ce qui signifie qu'ils peuvent être mis à jour et ne sont pas limités à une certaine fenêtre de temps afin qu'ils puissent détecter des attaques complexes.
Real-world incidents detected in Stellar Cyber:
  • Attaque Darkside Ransomware
  • Attaque par coup de soleil

How Stellar Cyber’s AI Engine Works

Fonctionnalités clés

Précis

Alert Fatigue is a serious problem. Not every anomaly is
a security incident. Analystes de sécurité should stop sifting through
countless anomalies and focus on the real threats. Core to
Ouvrez XDR, Stellar Cyber’s AI Engine leverages
state-of-the-art machine learning algorithms to implement
the best accuracy for detection. It analyzes time series and
peer groups with unsupervised learning, performs complex
behavior analysis through modeling relationships with Graph
ML, and generalizes known attack patterns with supervised
learning. It also correlates and builds context with advanced
Graph ML, so that we can present the high priority attacks with
rich context.

Temps réel

It may take minutes for hackers to infiltrate your system and
steal valuable information. You need virtual security experts to
continuously work around the clock and detect threats in real
time. Stellar Cyber’s AI Engine performs ML inference in real
time and provides detailed reasons for its output.

Unified

Notre moteur d'IA avancé unique alimente Stellar Cyber's Ouvert
XDR
technology and works on various data sources after
normalization regardless of data types such as logs or
network traffic. When a new data source is ingested, all
existing detections will be directly applied. For example, our
machine learning can perform user behavior analysis based
on behavior data from different data sources. Machine
learning inference is natively embedded in our data
processing pipeline without the need to send data outside.

Adaptatif

Stellar Cyber goes wherever you need it to go – on-premise,
in the cloud or hybrid. Multi-tenancy is built in from the
beginning to ensure flexible, secure operations for any
organization. Multi-site allows data to stay resident in its own
region to be compliant and scalable in complex operating
environnements.

Explicable et exploitable

The ultimate goal for detection is to take action to stop attacks
and to keep your environment safe. Action-taking is a serious
décision; analystes de sécurité need to fully understand the situation
in order to make an informed decision regarding what is the
best action to take. With the latest explainable AI, instead of
being a black box, the AI Engine provides human-friendly
evidence and easy-to-digest-details from ML models to ease
decision-making. With that, analystes de sécurité peut facilement
understand the reasons and evidence for any detection in order
to block an attack with high confidence without mistakenly
interrupting protected users or applications.