Biometric Identification Using Deceiving Prints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric identification systems are vulnerable to fraud techniques that analyze power consumption, execution time, and electromagnetic radiation to manipulate candidate prints and deceive the identification algorithm, making it difficult to resist attacks that modify inputs to achieve a valid score.
Innovation Solution
The method involves comparing candidate prints with both reference prints and deceiving prints, generating and modifying deceiving prints to maintain a consistent validation threshold, thereby misleading attackers and complicating the analysis of the identification algorithm, while ensuring constant identification time and resistance to successive presentations of similar prints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the identification system compares candidate prints only with reference prints, then the identification process is simple and fast, but the system becomes vulnerable to fraud techniques that analyze power consumption and execution time
Solution Approach 1:
The patent introduces deceiving prints as intermediary elements between the candidate print and the reference print. These deceiving prints act as mediators that consume computational resources and mask the actual identification process, making it difficult for attackers to analyze power consumption and execution time patterns. The deceiving prints are generated dynamically and compared with candidate prints before or instead of comparing with reference prints, thereby protecting the reference prints from direct analysis while maintaining identification functionality.
Solution Approach 2:
The identification system combines multiple types of prints (reference prints and deceiving prints) into a composite comparison structure. This composite approach mixes legitimate reference data with artificial deceiving data, creating a complex comparison environment that obscures the actual identification process from attackers analyzing power consumption and execution time, while still allowing valid identifications to succeed.
2Reliability
If the system generates and compares with multiple deceiving prints, then fraud resistance improves, but the execution time and computational resources increase
Solution Approach 1:
The system implements periodic action by selectively comparing candidate prints with deceiving prints based on specific conditions. Rather than always comparing with all possible deceiving prints, the system periodically introduces deceiving print comparisons when fraud risk is detected or when the same candidate print is presented multiple times with slight modifications. This periodic approach maintains fraud resistance while controlling execution time by not always performing the additional comparisons.
Solution Approach 2:
The system changes parameters dynamically by adjusting the number and type of deceiving prints generated based on the characteristics of the candidate print and the context of the identification attempt. When a candidate print shows signs of being part of a fraud attack (such as slight modifications to the same print), the system increases the use of deceiving prints. For normal identifications, it reduces or eliminates deceiving print comparisons, thereby optimizing execution time while maintaining fraud resistance when needed.
Data Source
AI summary
A biometric identification method includes the steps of comparing a candidate print with a reference print and of validating the identification according to a certain number of characteristics common to both prints and a predetermined validation threshold. The method includes the steps of creating at least one deceiving print and comparing same with a candidate print. An identification device designed for implementing this method is also provided.