Abnormality Detection Model for Request Security
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current solutions fail to effectively detect abnormal requests in public computing environments, which can lead to security issues such as data theft and malicious data modification, especially for applications deployed across multiple client terminals.
Innovation Solution
A method that acquires information related to target requests and context requests, converting this information into a vectorized feature representation, and using an abnormality detection model to determine whether the target request is abnormal, thereby enhancing security by considering the request context.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional security detection methods are used, then the system is simple to implement, but the detection accuracy of abnormal requests is insufficient
Solution Approach 1:
The patent replaces traditional rule-based mechanical detection systems with an intelligent abnormality detection model based on machine learning. The model transforms request information into vectorized feature representations and automatically identifies abnormal patterns, substituting manual security rule configuration with adaptive intelligent detection that improves accuracy while managing complexity through automated learning.
Solution Approach 2:
The patent changes the parameter representation of requests by converting structured request information into vectorized feature representations. This transformation enables the detection model to process and analyze request patterns in a continuous vector space, allowing for more nuanced detection of abnormal behaviors compared to discrete rule-based parameters.
2Measurement precision
If context information is not considered, then the detection process is fast, but the identification accuracy of request normality is reduced
Solution Approach 1:
The patent applies preliminary action by pre-processing request information into vectorized feature representations before detection. This preparation step organizes the data in advance, allowing the detection model to quickly process contextual information during actual detection without significant time penalty, thereby maintaining both accuracy and speed.
Solution Approach 2:
The patent adds the dimension of context information to the detection process by incorporating multiple request attributes and historical patterns into the vectorized representation. This multi-dimensional feature space enables the model to consider contextual relationships while maintaining efficient processing through optimized vector operations.
3Measurement precision
If vectorized feature representation and machine learning models are used, then detection accuracy improves, but computational complexity increases
Solution Approach 1:
The patent applies partial action by selectively processing only the most relevant request information into vectorized features, rather than analyzing every possible attribute in full detail. This approach achieves sufficient detection accuracy by focusing on key discriminative features while reducing overall computational burden and resource consumption.
Data Source
AI summary
The present disclosure relates to a method, a device, and a computer program product for abnormality detection. The method provided by embodiments of the present disclosure includes: acquiring information related to a target request initiated by a client terminal to an application and at least one context request, the information at least indicating the type and initiation time of the target request and the type and initiation time of the at least one context request; converting the acquired information into a vectorized feature representation for the target request; and determining an abnormality detection result of the target request based on the vectorized feature representation and using an abnormality detection model, the abnormality detection result indicating whether the target request is an abnormal request, and the abnormality detection model characterizing a correlation between a vectorized feature representation for a request and an abnormality detection result.