Outbound Traffic Anomaly Scoring for Network Security

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Computer networks face challenges in detecting malicious outbound traffic due to the difficulty in identifying new command and control centers, leading to unfettered access for malicious parties until an exploit is recognized, and existing solutions suffer from high false positives and user fatigue.

Innovation Solution

A system that detects emergent abnormal behavior in computer networks by scoring outbound communications based on feature pairs and aggregating scores to provide near real-time security alerts without relying on blacklists, differentiating between anomalous and widespread behaviors to reduce false positives.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If blacklists are used to block known command and control centers, then known threats are blocked, but new command and control centers cannot be identified in time

Engineering Contradiction:
Improvethreat blocking effectivenessVSAvoiddetection time for new threats
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of outbound traffic patterns, device behaviors, and network metadata before malicious activity is confirmed. By continuously monitoring and scoring potential anomalies in advance, the system can rapidly respond to new command and control centers without waiting for blacklist updates or manual analysis.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements continuous feedback loops where detected anomalies are scored, aggregated, and used to update detection models in real-time. This feedback mechanism allows the system to adapt to new threats dynamically, improving detection of emerging command and control centers while maintaining reliability against known threats.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If traditional detection methods are used, then security threats are identified, but false positives cause user fatigue

Engineering Contradiction:
Improvethreat detection accuracyVSAvoidanalyst workload
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system applies different scoring criteria and aggregation methods to different types of traffic and devices based on their specific characteristics. By tailoring the detection approach to local contexts (device type, network role, traffic patterns), the system improves detection precision while reducing false positives that would otherwise contribute to analyst fatigue.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system dynamically adjusts detection parameters and scoring thresholds based on aggregated abnormality scores and incident scores. By changing parameters adaptively rather than using fixed thresholds, the system maintains high detection accuracy while filtering out false positives, thereby reducing the workload on security analysts.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If comprehensive traffic analysis is performed, then detection accuracy improves, but processing time and complexity increase

Engineering Contradiction:
Improveanomaly detection accuracyVSAvoidsystem processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the traffic analysis process into distinct scoring stages (anomaly scoring, aggregation, incident scoring) that can be processed independently and in parallel. This segmentation reduces processing complexity by breaking down comprehensive analysis into manageable components while maintaining overall detection accuracy through the cumulative effect of multiple scoring layers.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3552363B1Near real-time detection of suspicious outbound traffic
Publication Date: 2021.04.28 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3552363B1 patent drawingFigure 1
  • EP3552363B1 patent drawingFigure 2
  • EP3552363B1 patent drawingFigure 3

AI summary

Detecting emergent abnormal behavior in a computer network faster and more accurately allows for the security of the network against malicious parties to be improved. To detect abnormal behavior, outbound traffic is examined from across several devices and processes in the network to identify rarely communicated-with destinations that are associated with rarely-executed processes. As a given destination and process is used more frequently over time by the network, the level of suspicion associated with that destination and process is lowered as large groups of devices are expected to behave the same when operating properly and not under the control of a malicious party. Analysts are alerted in near real-time to the destinations associated with the activities deemed most suspicious.