Philo-AD
Anomaly Pattern Detection Solution
Applies Deep learning artificial intelligence technology to effectively monitor suspicious behaviors and patterns from internal network as well as identify external threats.
The process is in real-time, and it supports instant update feature to maximize system reliability.
Since buying and running a computing power necessary to implement deep learning can be cost prohibitive, Ellexi offers monthly subscription based services for customers.
Traditional AI-based solutions
Learn after finding abnormal data one by one
Philo-AD
After learning the normal data first
Detect the part out of range as abnormal data
Minimizing progressive false positives using
a combination of deep neural networks and knowledge-based methods
The learning period, application period and cost can be reduced by up to 50%, and unknown risk factors can be identified
Features
Convenience
Assume every data is ‘Normal’, no tagging or labeling necessary
Precision
Gradually minimize false positive issues with anomaly pattern storage
Versatile
Customizable solution since it has been developed not just for a specific domain
Practical
Using technology that is required before applying the applied Neural network model by reinforcement learning, which is being actively researched
No Expert
No need of experts to generate rules by consulting, therefore minimize time and cost for deployment
Dashboard
Explainable
Explaining the reason and the cause of suspicious patterns (Anomalies)
3
Auto Learning
Automatically collects data-set for automated learning
2
Monitoring & Graph
Graphical presentation of monitoring, learning and verification process
Analytic graphic presentation of anomalies
1
Application
Finance
FDS
Data Collection
Analysis/Detection
Monitorting
SME Network Security
Web/Log analysis
Anomaly Detection
APT
ESM/IDS/IPS/DRM
Smart Factory
Process Management
Energy Management
Quality Analysis
Predictive Maintainance