Never miss a story

Get subscribed to our newsletter


×
Tweeters unable to automatically save tweets to facebook. Pixabay

Scientists have developed a new generic algorithm based on machine-learning to detect fake accounts on social network platforms including Facebook and Twitter, an advance with considerable potential for applications in the cyber-security arena.

“With recent disturbing news about failures to safeguard user privacy, and targeted use of social media to influence elections, rooting out fake users has never been of greater importance,” said lead researcher Dima Kagan from the Ben-Gurion University (BGU) in Israel.



Facebook has many fake profiles. Pixabay

The study showed that the algorithm is generic, and efficient both in revealing fake users and in disclosing the influential people in social networks. “Overall, the results demonstrated that in a real-life friendship scenario we can detect people who have the strongest friendship ties as well as malicious users, even on Twitter,” the researchers said.

Based on machine-learning algorithms, the new method, detailed in the journal Social Network Analysis and Mining, works on the assumption that fake accounts tend to establish improbable links to other users in the networks.

Also Read: Facebook Rolls Out Fact-Checking News In Karnataka

It constructs a link prediction classifier that can estimate, with high accuracy, the probability of a link existing between two users. It also generates a new set of meta-features based on the features created by the link prediction classifier.


Fake accounts on Twitter will be identifie too. VOA

Using the meta-features, the researchers, constructed a generic classifier that can detect fake profiles in a variety of online social networks. “We tested our algorithm on simulated and real-world data sets on 10 different social networks and it performed well on both,” Kagan said.

Previously, researchers from the BGU had developed the Social Privacy Protector (SPP) to help users evaluate their friends list in seconds to identify which have few or no mutual links and might be “fake” profiles. IANS


Popular

Kishu Inu and Dogelon Mars are some of the more popular canine coins in recent months. Their popularity is demonstrated by the vast amount of trading volume that these cryptocurrencies receive.

At the time of writing, Kishu Inu has a trading volume exceeding $10 million and Dogelon Mars has an even larger trading volume that surpasses $30 million.

Keep Reading Show less

HUH Token

It’s here, and it appears that there ain’t nothin’ or no one stopping the skyrocketing force of HUH Token and the release of the long-awaited White Paper is finally here and we’re living for it.

It’s also great to note that Shiba Inu made a triumphant crypto market return this week and the reign of the dog continues though with HUH Token’s White Paper release it could see the ‘Utimeme’ token break out of the atmosphere on its December 6th launch and surpass Shiba Inu for altcoin supremacy.

Keep Reading Show less

HUH Token

HUH Token has been on the lips of crypto lovers for some time now and the much-anticipated White Paper release is here, right now, today!

Not only this but Shiba Inu’s mastery of the altcoin world could be coming to an end on HUH Token’s December 6th release if the aims, goals and technology in the White Paper are anything to go by.

Keep reading... Show less