AI Security Selection for Resource-Aware Data Transmission

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data transmission systems lack effective methods to determine the need for security and apply optimal security techniques dynamically, balancing data sensitivity and computing resource efficiency.

Innovation Solution

Implementing Artificial Intelligence (AI) in the form of Machine Learning (ML) models to assess data sensitivity and resource availability, identifying suitable security techniques such as obfuscation, scrambling, anonymization, stenography, watermarking, and frequency hopping, and applying them during transmission.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If security techniques are applied to all data transmissions, then data security is improved, but computing resource efficiency deteriorates

Engineering Contradiction:

Improvedata securityVSAvoidcomputing resource efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system dynamically changes security parameters (type of encryption, level of protection) based on data sensitivity classification. Different data types receive different security treatments, optimizing the balance between security and resource consumption. Critical data receives stronger protection while less sensitive data uses lighter security measures.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

Security measures are applied locally to specific data elements based on their sensitivity rather than uniformly to all data. The system identifies and applies security techniques selectively to sensitive data portions, leaving non-sensitive data with minimal or no security overhead, thus improving overall computing efficiency.

Inventive Principle:

Principle #3Local quality

2Reliability

If AI/ML models are used to determine security needs, then security optimization is improved, but device complexity increases

Engineering Contradiction:

Improvesecurity optimizationVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The AI/ML models automatically analyze data characteristics and determine security requirements without manual intervention. The system self-configures security parameters based on learned patterns from historical data, reducing the need for complex manual security policy configuration and management.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The AI/ML model acts as an intermediary layer between data transmission requests and security implementation. It translates raw data characteristics into optimized security configurations, simplifying the overall system architecture by centralizing the decision-making process in a specialized component.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20260010621A1Artificial intelligence-based determination of data security techniques to be implemented for electronic data transmissions

Publication Date: 2026.01.08 BANK OF AMERICA CORP

AI summary

Implementation, either prior to or during data transmission, of artificial intelligence in the form of machine learning model(s) to (i) determine whether a specific data set requires security and, in response to determining that the data set requires security, (ii) identifying which security technique or combination of security techniques are most suitable/optimal for the data set. Subsequently, the identified security measures are applied to the data set prior to or during data transmission. The determination of whether to a data set requires security and the identification of the security techniques balances the need for security in terms of data sensitivity and/or criticality against availability and/or efficiency of computing resources required to perform/apply the security technique(s) to the data set.