Sunday September 23, 2018
Home Lead Story New algorithm...

New algorithm may help locate fake Facebook and Twitter accounts

Using the meta-features, the researchers, constructed a generic classifier that can detect fake profiles

0
//
39
Tweeters unable to automatically save tweets to facebook. Pixabay
Tweeters unable to automatically save tweets to facebook. Pixabay
Republish
Reprint

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.

The icon of Facebook.
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.

Twitter to soon release Snapchat like feature. VOA
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

Click here for reuse options!
Copyright 2018 NewsGram

Next Story

Twitter Gets a Bug And Releases DM’s of 3 Mn Users To a Third Party Application

Twitter said it found no sign that hackers accessed the exposed data.

0
Twitter
Twitter on a smartphone device. Pixabay

A bug in Twitter’s platform for third-party app developers exposed some Direct Messages (DMs) from nearly 3 million users to outsiders, the micro-blogging platform has admitted.

The bug ran from May 2017 and within hours of discovering it on September 10, Twitter said it fixed the bug to prevent data from being unintentionally sent to the incorrect developer.

“The bug affected less than 1 per cent of people on Twitter. The bug may have caused some of these interactions to be unintentionally sent to another registered developer,” Twitter said in a blog post on Saturday.

Twitter
Twitter Chief Executive Officer Jack Dorsey testifies before a Senate Intelligence Committee hearing on foreign influence operations and their use of social media on Capitol Hill. VOA

“In some cases, this may have included certain DMs or protected tweets, for example a Direct Message with an airline that had authorised an Account Activity API (AAAPI) developer.”

The Account Activity API allows registered developers to build tools to better support businesses and their communications with customers on Twitter.

Twitter currently has over 336 million users and one per cent means nearly 3 million of those were affected.

Twitter
The logo appears on a phone post on the floor of the New York Stock Exchange.. VOA

If your business authorised a developer using the AAAPI to access your account, the bug may have impacted your activity data in error.

“We’re very sorry this happened. If your account was affected by this bug, we will contact you directly through an in-app notice and on twitter.com,” said the company.

In May, the micro-blogging platform asked its 336 million users to change their password across its services after it discovered a bug that stored passwords in plain text in an internal system.

Also Read: A Rise in Pregnancy Phobia Due to Social Media Platforms

Twitter said it found no sign that hackers accessed the exposed data but advised users that they should enter a new password on all services where their current password has been used. (IANS)