Network Attack Prediction Using IGWO-BiLSTM Traffic Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network security systems struggle to proactively identify network attacks, particularly DoS and DDoS attacks, leading to resource waste and information leakage due to their passive nature and inefficiencies in detecting anomalies.
Innovation Solution
A network attack prediction method utilizing an improved grey wolf optimizer (IGWO) combined with Bidirectional LSTM (BiLSTM) to model network traffic, enabling the identification of anomalies by constructing a prediction model that distinguishes between normal and attack traffic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If passive security protection technologies (firewall, data encryption) are used, then network security is protected after attacks occur, but the system cannot proactively identify network attacks
Solution Approach 1:
The patent applies preliminary action by using the improved grey wolf algorithm to optimize BiLSTM model parameters in advance, enabling the system to proactively predict and identify network attacks before they fully manifest. The model is trained beforehand on normal and attack traffic patterns, allowing it to detect anomalies as they emerge rather than reacting after damage occurs.
2Extent of automation
If intrusion detection system is used to monitor network in real time, then network attacks can be perceived and response decisions provided, but the system complexity increases
Solution Approach 1:
The patent introduces an improved grey wolf optimization algorithm as an intermediary that automatically tunes the BiLSTM model parameters. This intermediary layer simplifies the overall system by automating the complex task of parameter optimization, reducing the need for manual configuration and expert intervention while maintaining high detection accuracy.
Solution Approach 2:
The system applies self-service through the grey wolf optimizer that automatically adjusts the BiLSTM model parameters based on performance feedback. The optimization process is self-directed, with the algorithm autonomously searching for optimal parameter combinations without external intervention, thereby reducing system complexity while maintaining effectiveness.
3Measurement precision
If traditional prediction models are used, then network traffic can be analyzed, but the prediction accuracy is insufficient leading to false positives and resource waste
Solution Approach 1:
The patent applies parameter changes by using the grey wolf optimization algorithm to dynamically adjust the BiLSTM model parameters (learning rate, hidden layer units, dropout rate, batch size) to optimal values. This optimization significantly improves prediction accuracy by finding parameter combinations that better capture network traffic patterns, thereby reducing false positives and the associated resource waste from investigating false alarms.
Data Source
AI summary
A network attack prediction method includes: performing preprocessing, time series modeling and data feature analysis on the network traffic data set; dividing the network traffic data set into a normal traffic data set and an attack traffic data set; initializing parameters of the improved grey wolf algorithm; constructing a prediction model and initializing parameters of the prediction model; using the grey wolf optimizer GWO search strategy to obtain a first candidate of the optimal grey wolf; using the hunting DLH search strategy to obtain another candidate of the optimal grey wolf; selecting an optimal candidate; updating Xi(t) with the optimal candidate; judging whether to iterate to the maximum iterations; obtaining an optimal parameter combination of the prediction model and training the prediction model; obtaining an optimized convergent prediction model and identifying anomalies caused by network attacks.