Did you know that monitoring Fraudulent brand use, Phishing and Fake social media profiles relies on an application that uses computer vision and machine learning techniques?
That's right, this application scans the content of the detected threat and identifies areas where there is the occurrence of logos previously registered for your brand. In order for this application to function optimally, it is essential to input your logos into the platform, including color variations, as shown in the example below:
In the case of the example, both images should be uploaded to the platform.
After this input, our model will be trained to detect similar images in the platform's threats. Thus, registering your brand's logos is very important both for the assertiveness of your detections and for the productivity of your screening.
Below is some information about the areas examined, for each type of threat:
Fraudulent brand use: top and bottom of the screenshot
Phishing: the top part of the screenshot
Fake social media profile: profile picture and cover photo (in case of Facebook threats)
Thanks to this technology, your monitoring is refined from the detection stage, as it enables us to reduce the number of false positives that arrive for your screening on the platform. In addition, at the screening stage, you will also have more robust resources at your disposal.
Once we have your brand logo registered in your Monitoring Settings, the Logo similarity attribute will become part of your detections – for the threat types mentioned above. This feature will also be available for use in Automations and can be used as a criterion for automatic ticket forwarding.
Finally, the Logo similarity analysis will also contribute to the generation of the risk level attribute for your threats, which can also be applied in your Automations.
If you have any questions, feel free to reach out at [email protected] 😊