Ben-Gurion University of the Negev (Beer-Sheva, Israel) and University of Washington (Seattle) researchers have developed a new generic method to detect fake accounts on most types of social networks, including Facebook and Twitter.
According to a new study in Social Network Analysis and Mining, the new method is based on the assumption that fake accounts tend to establish improbable links to other users in the networks.
“With recent disturbing news about failures to safeguard user privacy, and targeted use of social media by Russia to influence elections, rooting out fake users has never been of greater importance,” explains Dima Kagan, lead researcher and a researcher in the BGU Department of Software and Information Systems Engineering. “We tested our algorithm on simulated and real-world data sets on 10 different social networks and it performed well on both.”
The algorithm consists of two main iterations based on machine-learning algorithms. The first constructs a link prediction classifier that can estimate, with high accuracy, the probability of a link existing between two users. The second iteration generates a new set of meta-features based on the features created by the link prediction classifier. Lastly, the researchers used these meta-features and constructed a generic classifier that can detect fake profiles in a variety of online 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 say. “Our method outperforms other anomaly detection methods and we believe that it has considerable potential for a wide range of applications particularly in the cyber-security arena.”
The Ben-Gurion University researchers previously 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.
The Latest on: Fake users
via Google News
The Latest on: Fake users
- Italy’s fake hospital conspiracy theory debunked as post-truth era takes holdon November 29, 2020 at 4:57 am
The worst part about a conspiracy theorist’s elaborate attempt at convincing the world of a giant COVID-19 hoax isn’t how easily it was debunked.
- Meet the man fighting the Chinese internet’s fake news epidemicon November 29, 2020 at 4:40 am
So much fake news from other countries is spilling over onto Chinese social media that a Shanghai journalist has started a fact-checking project for Chinese readers, many of whom have limited English ...
- Delhi man arrested for home loan frauds worth Rs 6.7 crores using fake IDson November 29, 2020 at 4:27 am
A man was arrested by the Economic Offences Wing of the Delhi Police for allegedly taking loans worth Rs 6.7 crores from three financial institutions on the security of a rented property in Delhis ...
- Recommended Reading: Using AI to create alarmingly realistic fake peopleon November 28, 2020 at 7:04 am
Fake personas on the internet are nothing new, but completely fake people that appear to be alarmingly real in photographs or animations are becoming increasingly common. To better understand how easy ...
- Fake unemployment claims letters, cash-loaded debit cards show up in some Louisiana mailboxeson November 27, 2020 at 4:00 pm
Residents across Louisiana have received letters tied to fake unemployment claims, approvals for benefits and even received debit cards loaded with cash benefits for people they don't know who are ...
- Over 60 Fake ‘Among Us’ Apps Discovered; Some Used As Malware Dropperson November 27, 2020 at 3:00 am
An app security company discovered that cybercriminals are now using fake "Among Us" apps to spread malware and adware.
- Attorney General warns of ‘cruel’ unemployment scam using fake Gmail accounton November 25, 2020 at 5:03 pm
Messages about state unemployment benefits from a Gmail account should not be trusted, the Michigan Attorney General warned Wednesday. People who filed a claim with the Unemployment Insurance Agency ...
- While Twitter was buzzing about a fake Parler data leak, a hacker says he actually breached some user data from the conservative social networkon November 24, 2020 at 4:00 pm
Hackers took data from a Parler email vendor, but the security of the platform itself is intact, the company's CEO says.
- Screeners at Syracuse airport using new TSA technology to detect fake IDson November 23, 2020 at 6:06 am
The Transportation Security Administration is using new technology to confirm the validity of travelers’ identification and verify their flight information. Syracuse Hancock International Airport ...
via Bing News