As malicious actors increasingly want to use social media platforms to spread misinformation, use phishing scams or to use other ominous motives, it is important that each platform continues to develop its detection processes, to protect users from exploitation and their keep feeds free of unwanted. distraction, which helps maximize engagement.
This week, Pinterest given an overview of its evolving efforts to detect and remove spam and malicious content, outlining how it detects problematic traces at the domain level, based on where scammers and spammers are looking to refer Pinners after clicking on the platform content .
As explained by Pinterest.
“One tactic that determines malicious actors is the misuse of the image of a pin and the link to a malicious external website. Our models detect spam vectors, such as Pin links, as well as users who handle spam. We limit the spread of spam. Pin fast with spam links and take immediate action against users who have been identified with high confidence to handle spam. “
The visual nature of Pinterest makes it a less receptive platform for live spam, as well as the increasing focus on shopping, which has changed how people use the app. Yet scammers, as Pinterest notes, will still try to mislead Pinners into their sites.
Therefore, Pinterest’s domain level approach is an important deterrent: by focusing on tracking scam sites, Pinterest can then systematically eliminate all links to each site, quickly disable the links and protect users.
“We are conducting a manual for those who have been identified with little confidence to limit false positives, and we are informing users of our actions to maintain transparency and also offer an option to appeal against our decision. To make an impact maximize, teach our model to classify a domain as spam rather than a link. We apply the same enforcement to all Pins with links belonging to the same domain. “
This is a good approach, and while not all platforms apply the same domain-level strategy, in Pinterest’s case, it’s an effective way to respond more quickly to such threats and provide more protection to users.
Pinterest also uses a similar process to track down problematic individuals.
“We use features created from user attributes and their past behavior as input. We also use user-domain interaction, summarized as a distribution of domain counts for each user where domain counts are reused from the spam domain model, as input. “
Pinterest therefore uses broader domain-level tracking to erase potentially problematic individuals, and then marks them for possible enforcement.
“We group users on features that can successfully isolate suspicious groups with high accuracy. Experts identify these features by examining the behavior of suspicious users and their use of resources for creating spam content.”
Through these extensive tracking systems, Pinterest is able to take broader, more engaging approaches to eliminate spam behavior, and again to better protect users and the user experience, by pushing it out before it can have a real impact.
It seems to be an effective approach to stop Pin abuse for such activities, with a wide application through the domain that facilitates faster shutting down of fraudulent networks.
Of course, no process is perfect, and there are still examples of pins being used to spread misinformation and other scams. But this system makes it much harder for scammers to work, by quickly eliminating large parts of the pen that refer to problematic domains in one step.
You can read more about Pinterest’s evolving spam detection processes here.