Dynamic Access Triggers Using Synthetic Networks for Attacker Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cyberattacks on databases storing sensitive information are becoming increasingly sophisticated, posing challenges in distinguishing between legitimate users and malicious actors, leading to resource wastage and potential data breaches.
Innovation Solution
A system and method using machine learning models to dynamically generate access triggers based on entity actions, identifying and filtering out malicious actors by generating dynamic triggers and synthetic network structures, thereby reducing processor and memory usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are used to dynamically generate access triggers and analyze entity actions, then security detection precision is improved, but device complexity increases
Solution Approach 1:
The patent introduces machine learning models as intermediary components that analyze entity actions and generate access triggers. These models act as mediators between raw entity behavior data and security decisions, enabling sophisticated detection without requiring complex rule-based systems throughout the entire architecture.
Solution Approach 2:
The patent replaces traditional mechanical rule-based security systems with machine learning-based automated analysis. Instead of manually configured access control rules, the system uses ML models to dynamically generate access triggers based on entity behavior patterns, substituting mechanical decision-making with intelligent algorithms.
2Ease of operation
If all entities are granted access to network resources, then ease of operation is improved, but loss of energy increases due to resource wastage
Solution Approach 1:
The patent implements preliminary action by generating access triggers before entities actually access network resources. The machine learning model analyzes entity actions in advance and determines whether to grant access, preventing resource wastage before it occurs rather than detecting and responding to misuse after the fact.
Solution Approach 2:
The system uses feedback from entity actions to dynamically adjust access decisions. The machine learning model continuously monitors entity behavior and uses this feedback to generate appropriate access triggers, creating a closed-loop system that optimizes resource allocation based on actual usage patterns.
3Device complexity
If traditional access control methods are used, then device complexity is reduced, but measurement precision of suspicious activity detection deteriorates
Solution Approach 1:
The patent changes the parameters of access control from static rules to dynamic machine learning-based decisions. By transforming the decision-making parameters from predetermined conditions to adaptive behavioral analysis, the system achieves higher detection precision while maintaining manageable complexity through automated model training and inference.
Data Source
AI summary
A system comprises a memory communicatively coupled to at least one processor. The at least one processor is configured to receive communication feedback from an entity requesting to access network resources in a communication network and execute a machine learning algorithm to determine intents based on the communication feedback and generate a synthetic network structure based on the determined intents. Further, the processor is configured to present access to the synthetic network structure to the entity in the communication network, determine that the entity performed one or more actions associated with the synthetic network structure in response to receiving the dynamic trigger from the communication network, determine that the entity is associated with an electronic attacker, generate a report comprising that the entity is associated with the electronic attacker, and train the one or more machine learning models using the report.