Dynamic Behavior-Based Access Control for Edge Devices

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The proliferation of edge devices in edge computing environments creates security challenges due to vulnerabilities in device security, as traditional systems lack the ability to adapt to changing configurations and diverse communication patterns, hindering the adoption of edge computing.

Innovation Solution

A dynamic, behavior-based adaptive access control system for edge devices that employs real-time monitoring, machine learning, and contextual decision-making to identify anomalous behavior, dynamically adjusting access permissions and integrating with threat intelligence sources for up-to-date threat mitigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional access control systems are used, then system simplicity is maintained, but the ability to adapt to changing configurations and diverse communication patterns of edge devices is lost

Engineering Contradiction:

Improveadaptability to changing configurationsVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The access control system dynamically adjusts access permissions based on real-time analysis of device behavior patterns. The system continuously monitors edge devices, learns their normal operational patterns through machine learning algorithms, and adapts access control decisions accordingly, transitioning from static to dynamic access management that responds to changing configurations and communication patterns

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system employs machine learning algorithms that automatically learn and adapt to device behavior patterns without requiring manual reconfiguration. The anomaly detection system self-adjusts by continuously analyzing operational data and updating its understanding of normal behavior, enabling autonomous adaptation to changing edge device configurations

Inventive Principle:

Principle #25Self-service

2Reliability

If machine learning-based anomaly detection is implemented, then security against unauthorized users is improved, but computational resources and processing time are increased

Engineering Contradiction:

Improvesecurity reliabilityVSAvoidcomputational energy consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary learning of normal device behavior patterns during designated training periods before actual security threats occur. The machine learning algorithms continuously update their models during normal operation, preparing anomaly detection capabilities in advance so that when threats occur, the system can respond quickly without requiring intensive real-time computational resources for learning

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces traditional rule-based security mechanisms with machine learning-based anomaly detection. Instead of relying on pre-defined security rules that require continuous manual updates, the system uses algorithms that automatically learn from operational data, substituting mechanical rule-matching processes with intelligent pattern recognition that adapts to changing conditions

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Difficulty of detecting and measuring

If real-time monitoring of edge devices is implemented, then anomaly detection capability is improved, but data processing load and system complexity are increased

Engineering Contradiction:

Improveanomaly detection capabilityVSAvoiddata processing complexity

Core Design Contradiction:

Difficulty of detecting and measuringVSDevice complexity

Solution Approach 1:

The system extracts and focuses monitoring on specific critical behavior patterns and parameters rather than processing all device data uniformly. By identifying and isolating the most relevant operational indicators for anomaly detection, the system reduces the complexity of data processing while maintaining effective monitoring of security-relevant behaviors

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The anomaly detection system applies different analysis depths and methods to different device behaviors and parameters based on their security relevance. Critical security-related operations receive intensive monitoring and analysis, while less critical operations are monitored at lower detail levels, optimizing the balance between detection capability and processing complexity

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12450112B2Dynamic behavior-based adaptive access control system for edge devices

Publication Date: 2025.10.21 DELL PROD LP

AI summary

A method comprises receiving data corresponding to operation of one or more edge devices, and analyzing the data using one or more machine learning algorithms to determine whether the operation of the one or more edge devices is anomalous. In determining whether the operation of the one or more edge devices is anomalous, the one or more machine learning algorithms determine whether the operation of the one or more edge devices deviates from identified normal operational parameters of the one or more edge devices. At least one action to control access to the one or more edge devices is triggered in response to determining that the operation of the one or more edge devices is anomalous.