Sift Science. has filed a patent for a method using machine learning to detect automated fraud or abuse attacks online. The process involves analyzing digital activity signatures, computing encoded representations, and implementing threat mitigation actions based on the origin of the attack. GlobalData’s report on Sift Science gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Sift Science, AI-assisted threat classification was a key innovation area identified from patents. Sift Science's grant share as of January 2024 was 79%. Grant share is based on the ratio of number of grants to total number of patents.
Detection of automated online fraud or abuse
A computer-implemented method for detecting automated online fraud or abuse has been filed as a patent (Publication Number: US20230421584A1). The method involves sourcing digital event data from online activities, extracting features from the data, converting them into an encoded graphical representation using an autoencoder model, and classifying the representation into distinct fraud attacks or abuses. Based on this classification, automated threat mitigation actions are selectively implemented to address the identified fraud or abuse.
The method further includes steps such as generating vector embeddings, computing the graphical representation, defining search queries, and executing searches in an n-dimensional space to identify clusters associated with specific fraud attacks or abuses. By mapping the encoded representation to these clusters and computing distances between vector embeddings, the method effectively categorizes and responds to potential threats. Additionally, the patent outlines the construction of an automated fraud or abuse signature registry, composed of distinct activity sequences and associated metadata, to enhance the detection and mitigation of online fraud or abuse activities executed by malicious bots. The method aims to prevent web-enabled services from processing fraudulent data to completion by implementing appropriate threat mitigation actions based on the identified classification.
To know more about GlobalData’s detailed insights on Sift Science, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
