Artificial Intelligence (AI) has many applications. It is poised to make our life simple and secure. Companies like Microsoft are trying to adapt to this modern technology as quickly as possible to use it to their advantage. For instance, AI techniques can be used to overcome the increasing challenges of online fraud. Microsoft has been at the forefront of this trend. It is using AI running in the cloud to find scams.
Microsoft Uses AI To Track Down Tech Support Scams
A team at Microsoft created a model that looked for content that behaved in a way that was consistent with a Tech Support Scam, such as creating a pop-up that refreshed in microseconds to give the appearance it wasn’t going away.
Thereafter, the team thoroughly searched the web for those sites displaying these attributes and captured screen shots of all the content that could potentially be a scam. Manually scanning all of them in questionable pieces of content found, wouldn’t have been easy. So, the software giant resorted to a subset of Artificial Intelligence called Machine Learning to sort the data.
While working on this project, the team used custom AI tools, running on Microsoft’s Azure cloud computing platform, to look for image similarity, content and other visual clues that would closely resemble the pop-up to the fraud under investigation.
It, then used the computer vision API from Microsoft Cognitive Services to scan the ads for phone numbers and other bits of information that could provide clues as to their origin.
Thus, by using AI, the team was able to quickly track the fast-moving scammer. In the absence of this, approaching the problem manually by deploying thousands of employees to document complaints and then trying to figure out if the data captured pointed to a specific pattern would have taken unusually long time.
The experiment also revealed something important – only a fraction of victims report Tech Support Scams to cyber authorities.