Multi-Target Neural Network for Security Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional machine learning-based security recognition systems ignore available metadata during training, leading to suboptimal performance in detecting malware and other security threats.
Innovation Solution
A system that incorporates metadata into the training process of a machine learning model, specifically a multi-target neural network, to enhance its ability to recognize security threats by jointly optimizing security recognition and auxiliary information loss functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional machine learning models are trained only on security recognition labels, then the training process is simple, but the model performance is suboptimal
Solution Approach 1:
The patent combines multiple training objectives into a single unified training process. The model simultaneously learns to predict security recognition labels and auxiliary information (metadata) from the same training data, merging what would traditionally be separate training processes into one integrated approach that improves overall model performance
Solution Approach 2:
The training model is designed to serve multiple functions: it performs the primary security recognition task while simultaneously learning patterns from auxiliary metadata. This multi-functional training approach allows the model to leverage additional information sources without requiring separate specialized models for each task
2Reliability
If multiple separate models are trained for different security tasks, then each model can be optimized for its specific task, but the system complexity and maintenance burden increase
Solution Approach 1:
The patent merges multiple security recognition tasks into a single multi-target model that handles both primary labels and auxiliary metadata prediction. This consolidation reduces the number of separate models that need to be trained, deployed, and maintained while still allowing each task to receive dedicated optimization through task-specific loss functions
Data Source
AI summary
A system for conducting a security recognition task, the system comprising a memory configured to store a model and training data including auxiliary information that will not be available as input to the model when the model is used as a security recognition task model for the security recognition task. The system further comprising one or more processors communicably linked to the memory and comprising a training unit and a prediction unit. The training unit is configured to receive the training data and the model from the memory and subsequently provide the training data to the model, and train the model, as the security recognition task model, using the training data to predict the auxiliary information as well as to perform the security recognition task, thereby improving performance of the security recognition task. The prediction unit is configured to use the security recognition task model output to perform the security recognition task while ignoring the auxiliary attributes in the model output.