Additional Info

Company Separatorbuguroo
Companybuguroo
Websitehttp://www.buguroo.com
Company size (employees)10 to 49
Type of solutionCloud/SaaS

Overview

bugFraud is the most comprehensive solution to prevent online fraud based on a frictionless and agentless approach. Its holistic view includes several sources to find any suspicious pattern on user’s behavior and their environment. To prevent the online fraud, isolated solutions which focus just on some points are not enough.

bugFraud is able to identify whenever an user is being impersonated by a fraduster taking care about how each user specifically interacts with our customers’ website or APP mobile profiling the devices, networks used (geolocation, reputation, anonimization,etc), behavioral biometrics (mouse, keyboard, touchpad, screen, etc) and much more to identify if the fraud could happen.

In addition, bugFraud has the most effective approach to detect whatever a malware injects in the browser while the users are navigating our customers website. Avoid false positives and minimize false negatives detecting even the most updated and sophisticated malware threats.

With all this information, bugFraud enrich his proprietary Deep Learning systems in order to make a risk score decision: user is at risk or not. Moreover, if the user is at risk, attacks like RAT, MitB, webinjects, ATO, Phishing,etc can be automatically stopped by bugFraud’s transparent countermeasures or can be reported to third party systems (i.e: transaction monitors,SIEM.etc)

bugFraud’s unique user-centric vision where each user owns a single Deep Learning model perfectly adapted to recognize himself/herself, allow our customers to profile fraudsters who usually changes their targets. It is not something related with you are good or bad, is much more,something related with Identity proofing and how to catch the fraudster making invisible relationships between our customers. The target can changes the fraudster not.

How we are different

1. Holistic view: including the more comprehensive approach to detect targeted malware injections (recognized by Gartner), Behavioral biometrics to profile how the user is and environment diagnosis to find any kind of anomaly in the device, network, etc.


2. AI models per registered user: not enough to classify in clusters (good/bad).Each fraudster or user is different so you need to know exactly how he/she behaves and which are his/her patterns. To generalize is not the way to caught individuals.


3. Deep Learning models for fraud prevention: more precise and adaptable to the everchanging fraud landscape than Machine Learning traditional models.