Voice Call Trustworthiness Scoring via Audio Characteristic Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional systems for preventing malicious voice communications are inadequate, as they rely on manual reporting by recipients and are ineffective against mass scams, with caller ID spoofing making it difficult to identify suspicious calls.
Innovation Solution
A computer-implemented method that identifies incoming voice calls, extracts characteristics, calculates a trustworthiness score based on recipient responses, and stores this score in a reputation database to enable security actions on matching calls, using machine learning algorithms to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional manual reporting systems are used to identify suspicious calls, then system complexity is reduced, but detection reliability and productivity deteriorate due to lack of automated detection and insufficient data collection
Solution Approach 1:
The system performs preliminary actions by automatically collecting call characteristics and calculating trustworthiness scores before manual reporting is needed. The reputation database pre-processes call data by extracting characteristics, comparing them against known scam patterns, and generating trustworthiness scores in advance, so when a call needs to be reported or blocked, the detection work is already completed.
Solution Approach 2:
The system enables self-service detection by automatically analyzing call characteristics and generating trustworthiness scores without requiring user intervention. The reputation database autonomously compares incoming call characteristics against stored patterns and provides detection results, freeing users from manual analysis while improving detection consistency and reliability.
2Measurement precision
If caller identification spoofing is used by scammers, then ease of operation for malicious callers is improved, but detection precision deteriorates because traditional caller ID cannot reliably identify suspicious calls
Solution Approach 1:
Instead of relying on the original caller ID which can be spoofed, the system creates a copy or alternative representation of call identity through trustworthiness scores derived from multiple characteristics. The reputation database stores and compares these characteristic profiles, allowing the system to identify scam calls based on their behavioral patterns rather than their spoofed identifiers, thus maintaining detection precision despite caller ID manipulation.
Solution Approach 2:
The system shifts from using a single parameter (caller ID) to multiple parameters (call characteristics, trustworthiness scores, reputation metrics) for identification. By changing the detection parameters from static caller ID to dynamic multi-dimensional characteristics including call duration, response patterns, and reputation scores, the system achieves detection precision that is resistant to spoofing while scammers continue to operate with ease using traditional methods.
3Productivity
If automated detection systems are implemented to identify suspicious calls, then productivity and detection speed are improved, but device complexity and computational requirements increase
Solution Approach 1:
The detection system is segmented into modular components: call characteristic extraction, trustworthiness score calculation, reputation database storage, and comparison analysis. Each module performs a specific function independently, allowing the system to achieve high detection productivity through automated parallel processing while managing computational complexity by dividing the overall task into manageable, reusable segments that can be optimized individually.
Data Source
AI summary
The disclosed computer-implemented method for detecting suspicious voice calls may include (i) identifying an incoming voice call, (ii) extracting, from audio of the incoming voice call, a plurality of characteristics, (iii) calculating a trustworthiness score of the plurality of the characteristics based on a response by a recipient of the incoming voice call, and (iv) storing the trustworthiness score of the plurality of characteristics in a reputation database that (a) receives a request for the trustworthiness score, the request originating from an additional computing device and including an additional plurality of characteristics extracted from an additional incoming voice call, (b) determines that the additional plurality of characteristics matches the plurality of characteristics, and (c) enables the additional computing device to perform a security action on the additional incoming voice call by sending the trustworthiness to the additional computing device. Various other methods, systems, and computer-readable media are also disclosed.