Deep Learning Facial Recognition for Secure Attended RPA

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Robotic process automation (RPA) systems face heightened data breach risks due to vulnerabilities in digital environments, particularly when attended robots handle confidential data, necessitating enhanced security measures.

Innovation Solution

Implementing a facial recognition framework using deep learning for attended robots to authenticate users before allowing access to sensitive data or systems, adding an additional security layer to RPA workflows.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If facial recognition authentication is implemented for attended robot RPA, then security against data breaches is improved, but device complexity increases

Engineering Contradiction:

ImprovesecurityVSAvoiddevice complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The facial recognition framework is nested within the existing RPA system architecture. The authentication module is integrated into the robot's operational workflow, where the robot captures facial images, processes them through deep learning models, and authenticates users before allowing access to confidential data or systems. This nesting approach enhances security without requiring a completely separate system.

Inventive Principle:

Principle #7Nested doll (Nesting)

Solution Approach 2:

The patent introduces an intermediary authentication layer between the user and the RPA system. The facial recognition framework acts as a mediator that verifies user identity before granting access to sensitive operations. This intermediary mechanism improves security by adding biometric verification while maintaining the existing RPA workflow structure.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If facial recognition framework with deep learning is added to RPA system, then authentication security is improved, but processing time increases

Engineering Contradiction:

Improveauthentication securityVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by capturing and processing facial images at the point of authentication need. The robot captures the facial image when the user attempts to access confidential data or initiate sensitive RPA operations, processes it through the deep learning framework, and makes authentication decisions in real-time within the workflow.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical authentication methods (such as password entry or physical tokens) with biometric facial recognition. This substitution uses deep learning-based image processing and pattern recognition algorithms to verify identity, providing more secure authentication while integrating seamlessly into the digital RPA environment.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12547692B2Facial recognition framework using deep learning for attended robots

Publication Date: 2026.02.10 UIPATH INC

AI summary

A facial recognition framework may be configured for robotic process automation (RPA) to automate a workflow for an application interface. A set of images of a user may be captured after the robot is initiated for the automated workflow. The set of images may be utilized by a deep learning neural network model to identify facial characteristics. The automated workflow may be performed by an attended robot based on successful validation of the user with the facial characteristics and credentials of the user for the attended robot.