Header Similarity Analysis for Bulk Email Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting unsolicited bulk electronic messages are inefficient in identifying such messages, especially when senders obscure their headers or contents, leading to increased network bandwidth waste and user frustration.
Innovation Solution
The method involves parsing and analyzing header fields of electronic messages to form feature vectors, computing an inner product for similarity measurement, and using insertion/deletion polymorphism tests to identify bulk messages, even with minor alterations, thereby blocking them at network junctures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If hash value comparison is used to identify bulk messages, then processing time is reduced, but only exact copies can be identified and any modification causes failure to recognize
Solution Approach 1:
The patent transforms the detection approach from exact hash matching to similarity-based detection by changing the parameter from binary match/no-match to a continuous similarity score. This allows the system to detect bulk messages even when senders modify headers or content slightly, while still maintaining efficient processing through mathematical operations on feature vectors.
2Measurement precision
If context analysis with keyword usage is used to discern UBE, then detection accuracy improves, but desired email may be wrongly characterized and user review is required
Solution Approach 1:
The patent moves from discrete keyword matching to continuous similarity scoring using inner products of feature vectors. This parametric approach provides more nuanced detection that reduces false positives, thereby decreasing the need for manual user review while maintaining high detection accuracy.
3Measurement precision
If automated context analysis is used to examine message contents, then UBE identification improves, but delivery delay increases particularly at large organizations
Solution Approach 1:
The patent performs similarity analysis on message headers and feature vectors before full message delivery, enabling early detection of bulk messages. This preliminary action allows the system to block suspicious messages quickly without requiring complete message examination, thereby reducing delivery delays while maintaining detection accuracy.
4Measurement precision
If protocol examination for specific language is used to identify undesirable email, then detection capability improves, but processing power requirements and costs increase
Solution Approach 1:
The patent extracts only the essential feature vectors from message headers and bodies, rather than examining entire message contents or performing comprehensive protocol analysis. This extraction approach maintains detection capability by focusing on key characteristics while significantly reducing processing power requirements and associated costs.
Data Source
AI summary
Methods, apparatuses, and computer-readable media for detecting bulk electronic messages using header similarity analysis. Bulk electronic messages can be detected by parsing (115) header fields of an electronic message; associating (120) at least one constituent unit with each header field defining a set of constituent units for each header field; ascertaining (230) a feature vector for each set of constituent units; forming (240) a collection of feature vectors; and computing (250) an inner product from a set of constituent units from an additional electronic message and the collection of feature vectors from the initial electronic message resulting in a measure of similarity between the initial electronic message and the additional electronic message.