Call Classification Using Probabilistic Hashes for Data Privacy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for recognizing undesirable calls on remote devices compromise the security of user data, particularly personal and biometric data, due to the transmission and analysis of unique identifiers without adequate depersonalization.
Innovation Solution
A system and method that generates probabilistic hashes from unique call identifiers on a secure device, applies frequency analysis to identify suspicious calls, and requests additional data only when necessary to recognize undesirable calls, ensuring data security by minimizing identifiable information transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If unique call identifiers are transmitted to remote devices for analysis, then the accuracy of recognizing undesirable calls is improved, but the security of user personal data is compromised
Solution Approach 1:
The patent introduces a probabilistic hash as an intermediary between the unique call identifier and the remote analysis system. This hash function transforms the original identifier into a depersonalized form that retains useful patterns for spam detection while eliminating direct personal information, thus serving as a mediator that protects user data privacy while enabling accurate call classification.
Solution Approach 2:
The patent changes the parameter representation of call identifiers by applying probabilistic hashing. This transformation modifies the data format from raw personal identifiers to hashed values with specific probabilistic properties, allowing the system to maintain detection accuracy through statistical patterns while changing the fundamental nature of the transmitted data to protect privacy.
2Reliability
If more data is requested from secure devices to improve classification accuracy, then the reliability of call recognition is improved, but the amount of sensitive data transmitted increases
Solution Approach 1:
The patent applies partial action by requesting only the probabilistic hash of the call identifier rather than the complete original data. This selective data transmission approach obtains sufficient information for reliable call recognition while minimizing the quantity of sensitive data transferred, achieving the right balance between reliability and data privacy protection.
Data Source
AI summary
Disclosed herein are systems and methods for recognizing undesirable calls on a remote device. In one aspect, an exemplary method comprises, generating, for each call, a call identifier from a probabilistic hash received from a secure device, the probabilistic hash having been computed by the secure device based on a unique call identifier associated with call data collected for the call; analyzing the generated call identifiers to identify at least one of the generated call identifiers as a suspicious call identifier; requesting data, from the secure device associated with the suspicious call identifiers, where the requested data includes at least information about the call associated with the suspicious call identifier; and analyzing data received in response to the request and recognizing suspicious call identifier and the call associated with the suspicious call identifier as undesirable based on the analysis of the data received in response to the request.