Anonymous IoT Device Behavior Monitoring via Data Anonymization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solutions for monitoring and analyzing smart device behaviors in the 'Internet of Things' networks are not privacy-preserving, as they do not anonymize behavior information before transmission, which can reveal sensitive user data, and are not suitable for devices with varying processing capabilities, impacting performance and power utilization.
Innovation Solution
The implementation of automated anonymous crowdsourcing methods that anonymize device behavior vectors by removing user-identifying information and transmit them over networks, using processor-executable instructions and multi-technology communication devices to monitor and analyze device behaviors, allowing for real-time detection and correction of anomalous behaviors without exposing personal information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If device behavior information is collected and transmitted for analysis, then device performance monitoring and anomaly detection capability is improved, but user privacy is compromised due to transmission of identifiable data
Solution Approach 1:
The patent extracts and removes user-identifying information from device behavior data before transmission. The anonymization process specifically extracts identifiers such as device IDs, user profiles, and location data, leaving only behavioral patterns for analysis. This resolves the contradiction by maintaining anomaly detection capability while eliminating privacy exposure risks.
Solution Approach 2:
The patent introduces an intermediary anonymization layer between data collection and data transmission. This intermediary process transforms identifiable behavior data into anonymized behavior patterns, acting as a mediator that preserves analytical value while removing harmful identifying information. The anonymized data serves as an intermediate representation that enables remote analysis without exposing user privacy.
2Loss of information
If comprehensive behavior monitoring is implemented across diverse IoT devices, then device performance insights are improved, but system complexity increases due to varying processing capabilities
Solution Approach 1:
The patent changes the parameters of behavior data from device-specific detailed metrics to standardized behavior patterns. By transforming diverse device behaviors into a common anonymized format, the system accommodates devices with varying processing capabilities without requiring complex device-specific handling. This parameter transformation resolves the contradiction by maintaining information quality while reducing system complexity.
Solution Approach 2:
The patent creates a universal anonymized behavior data format that can be applied across all IoT devices regardless of their specific capabilities. The standardized behavior patterns serve multiple device types uniformly, eliminating the need for complex device-specific processing logic. This universality resolves the contradiction by enabling comprehensive monitoring while simplifying the overall system architecture.
Data Source
Figure 1A~1B
Figure 1C
Figure 2
AI summary
Methods, and devices implementing the methods, use device-specific classifiers in a privacy-preserving behavioral monitoring and analysis system for crowd-sourcing of device behaviors. Diverse devices having varying degrees of “smart” capabilities may monitor operational behaviors. Gathered operational behavior information may be transmitted to a nearby device having greater processing capabilities than a respective collecting device, or may be transmitted directly to an “always on” device. The behavior information may be used to generate behavior vectors, which may be analyzed for anomalies. Vectors containing anomaly flags may be anonymized to remove any user-identifying information and subsequently transmitted to a remote recipient such as a service provider or device manufacture. In this manner, operational behavior information may be gathered about different devices from a large number of users, to obtain statistical analysis of operational behavior for specific makes and models of devices, without divulging personal information about device users.