Trend-aware combo-squatting detection using RNN
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods are inadequate for detecting combo-squatted domains, which are generated by combining a brand's domain name with generic keywords for malicious purposes, as they fail to predict future squatted domains effectively.
Innovation Solution
A computer-implemented method that selects a target domain, stores sequences of previously detected combo-squatted domains, obtains trends associated with the target domain, and ranks likely words for future use in combo-squatted domains based on trend distributions using a hardware processor, employing a Recurrent Neural Network to combine similarity and temporal dependency scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional detection methods are used to identify combo-squatted domains, then existing squatted domains can be detected, but future squatted domains cannot be predicted effectively
Solution Approach 1:
The system performs preliminary actions by analyzing historical squatted domain patterns and current brand trends before actual squatted domains are created. The prediction model proactively identifies likely future squatted domains by combining past squatted domain data with current brand mention trends, enabling brands to register protective domains in advance before they are actually squatted
Solution Approach 2:
The system implements feedback by continuously monitoring and analyzing detected squatted domains to refine prediction accuracy. The model uses historical detection data as training input, and the detection results feed back into improving future predictions by updating the understanding of squatter behavior patterns and brand vulnerability trends
2Measurement precision
If a comprehensive analysis of all possible domain combinations is performed, then all potential squatted domains can be identified, but the computational complexity and time required increase significantly
Solution Approach 1:
The system applies local quality by focusing analysis on specific high-value brand domains and their associated trend data rather than performing uniform comprehensive analysis across all domains. The prediction model concentrates computational resources on generating trend distributions for particular brands based on their unique squatter history and current media presence, rather than treating all domains equally
Solution Approach 2:
The system changes parameters by transforming raw historical domain data and trend information into probabilistic predictions. The model converts qualitative trend data (brand mentions in media) and historical patterns into quantitative probability scores that rank likely future squatted domains, enabling efficient prioritization without exhaustive analysis
Data Source
AI summary
A computer-implemented method is provided for identifying words likely to be used in new combo-squatted domains of a target domain. The method includes selecting the target domain. The method further includes storing, in a memory device, a sequence of previously detected combo-squatted domains from period [t-W, t-1]. The sequence includes a set of words W. The method also includes obtaining trends associated with the target domain at time t. The method additionally includes obtaining, by a hardware processor responsive to the trends, a trend distribution associated with the target domain at time t. The method further includes ranking, by a likelihood, a set of words E that have been extracted from the trend distribution and are expected to be used in the future in the new combo-squatting domains, responsive to the set of words W.