LAYERED CYBERSECURITY USING SPURIOUS DATA SAMPLES

Organization Name

Capital One Services, LLC

Inventor(s)

Galen Rafferty of Mahomet IL (US)

Samuel Sharpe of Cambridge MA (US)

Brian Barr of Schenectady NY (US)

Jeremy Goodsitt of Champaign IL (US)

Michael Davis of Arington VA (US)

Taylor Turner of Richmond VA (US)

Justin Au-yeung of Somerville MA (US)

Owen Reinert of Queens NY (US)

LAYERED CYBERSECURITY USING SPURIOUS DATA SAMPLES - A simplified explanation of the abstract

This abstract first appeared for US patent application 18170492 titled 'LAYERED CYBERSECURITY USING SPURIOUS DATA SAMPLES

Simplified Explanation:

The patent application describes a computing system that iterates between adding spurious data to a dataset and training a model on the dataset. If the model's performance does not drop by more than a threshold amount, additional spurious data is added until the desired performance decrease is achieved. The system can determine the impact of each feature on the model's output and generate spurious data samples by modifying impactful features. It can repeatedly modify the spurious data in the dataset and identify cybersecurity incidents based on the stored spurious data.

Key Features and Innovation:

Iterative process of adding spurious data and training models
Impact analysis of features on model output
Generation of spurious data by modifying impactful features
Detection of cybersecurity incidents based on spurious data

Potential Applications: This technology can be applied in various fields such as cybersecurity, fraud detection, and anomaly detection in datasets.

Problems Solved: This technology addresses the need for efficient model training and cybersecurity incident detection in datasets.

Benefits:

Improved model performance through iterative data addition
Enhanced cybersecurity incident detection capabilities
Efficient analysis of feature impact on model output

Commercial Applications: Potential commercial applications include cybersecurity software, fraud detection systems, and data analysis tools for businesses.

Prior Art: Readers can start searching for prior art related to this technology in the fields of machine learning, cybersecurity, and data analysis.

Frequently Updated Research: Stay updated on research related to machine learning algorithms, cybersecurity incident detection, and data manipulation techniques.

Questions about the Technology: 1. What are the potential implications of this technology in the field of cybersecurity? 2. How does this technology improve the efficiency of model training and feature analysis?

Original Abstract Submitted

In some aspects, a computing system may iterate between adding spurious data to the dataset and training a model on the dataset. If the model's performance has not dropped by more than a threshold amount, then additional spurious data may be added to the dataset until the desired amount of performance decrease has been achieved. the computing system may determine the amount of impact each feature has on a model's output. The computing system may generate a spurious data sample by modifying values of features that are more impactful than other features. The computing system may repeatedly modify the spurious data that is stored in a dataset. If a cybersecurity incident occurs (e.g., the dataset is stolen or leaked), the system may identify when the cybersecurity incident took place based on the spurious data that is stored in the dataset.