Home > Identity Theft > Afraid of Catfishing? A New Tool Is Trying to Make the Internet Safer

Comments 0 Comments

Anyone who’s read oddly positive online reviews or happened on Twitter users with suspiciously large followings knows that the Internet is full of fakes. Bogus followers or fake reviews aren’t just annoying — they call into question the very notion of crowdsourcing, one of the Internet’s most valuable tools.

Researchers at Carnegie Mellon University are hard at work developing automated tools to separate fake from real, attempting to restore the credibility of the wisdom of crowds. They call their new system Fraudar, a play on the word radar, and it works by detecting users who are almost certainly real. The Fraudar algorithm is open source, meaning it’s free for any company to use.

Those who create fake reviews and followers have long been engaged in a cat-and-mouse game with sites that facilitate sharing. Simple techniques like buying Twitter followers still work, but they are fairly easily uncovered. You’ve probably seen Twitter users with huge numbers of followers and accounts followed, for example, which is a sign that the user simply engages in follow-for-follow schemes.

Taking that scheme to the next level, criminals create two layers of fake accounts — “fraud” and “accomplice.” Accomplices are designed to act more like real users, and work to connect with actual users. These accomplices then interact with “fraud” accounts – accounts used to sell 1,000 Twitter followers, for example, or to commit actual scams on online auction sites — lending them an air of legitimacy. These two-sided arrangements form what researches call a bipartite core.

Plotted on a graph, the lines between various users trying to game the system on both sides form a dense center, hence the name, said Christos Faloutsos, professor of machine learning and computer science at Carnegie Mellon.

“It creates a very strange constellation [wherein] 1,000 people agree to admire the same two or three people,” he said. “This is a red flag.”

To avoid detection, fake account managers further try to camouflage themselves by mixing in authentic users. That’s where you come in. If you’ve ever been proud that some seemingly Internet famous person asked to follow you, you were probably being used. Fake accounts also follow real famous folks, like Lady Gaga or President Barack Obama, to add additional camouflage.

“They do this to make their accounts look normal,” Faloutsos said. Such camouflage works more often than not, he added, because current methods to detect fakes are not “adversarially robust.”

Detecting Normal Activity

Fraudar works because, ironically, it’s good at spotting normal activity. It picks out likely real users, them separates them from the clusters it spots. When those are removed, the bipartite core can easily be revealed.

“The algorithm begins by finding accounts that it can confidently identify as legitimate — accounts that may follow a few random people, those that post only an occasional review and those that otherwise have normal behaviors. This pruning occurs repeatedly and rapidly,” Carnegie Mellon said. “As these legitimate accounts are eliminated, so is the camouflage the fraudsters rely upon. This makes bipartite cores easier to spot.”

The algorithm works in part because it’s capable of scanning massive amounts of data very quickly. In real-world experiments using Twitter data for 41.7 million users and 1.47 billion followers, Fraudar fingered more than 4,000 accounts not previously identified as fraudulent, including many that used known follower-buying services, Carnegie Mellon said.

“The algorithm is very fast and doesn’t require us to target anybody,” Faloutsos said. “We hope that by making this code available as open source, social media platforms can put it to good use.”

Twitter did not immediately respond to Credit.com’s request for comment on the experiments.

Ultimately, Carnegie Mellon hopes the tool can be used to spot fake product reviews, fake advertising offers and even politicians who exaggerate their Internet popularity.

During the previous presidential election cycle, there were accusations of fake followers. In 2011, Newt Gingrich was accused of buying nearly a million Twitter followers. Then in August 2012, a CNET report noted Mitt Romney gained 116,000 Twitter followers in one day, which was wildly out of pattern. The issue isn’t one-sided. The Daily Mail said Barack Obama has nearly 20 million fake followers.

The issue is important because if fake reviews are allowed to crowd out real content, users will begin to ignore them altogether.

“It’s widespread right now because it works,” Faloutsos said. “But it distorts reality and translates dollars into false impressions. We are trying to stop that.”

(Editor’s Note: Keeping a close eye on your credit can help you monitor for signs of identity theft following other forms of fraud that can occur over the internet, such as email phishing. You can view two of your credit scores, updated every two weeks, for free on Credit.com.)

Image: jean gill

Comments on articles and responses to those comments are not provided or commissioned by a bank advertiser. Responses have not been reviewed, approved or otherwise endorsed by a bank advertiser. It is not a bank advertiser's responsibility to ensure all posts and/or questions are answered.

Please note that our comments are moderated, so it may take a little time before you see them on the page. Thanks for your patience.

Credit.com receives compensation for the financial products and services advertised on this site if our users apply for and sign up for any of them.

Hello, Reader!

Thanks for checking out Credit.com. We hope you find the site and the journalism we produce useful. We wanted to take some time to tell you a bit about ourselves.

Our People

The Credit.com editorial team is staffed by a team of editors and reporters, each with many years of financial reporting experience. We’ve worked for places like the New York Times, American Banker, Frontline, TheStreet.com, Business Insider, ABC News, NBC News, CNBC and many others. We also employ a few freelancers and more than 50 contributors (these are typically subject matter experts from the worlds of finance, academia, politics, business and elsewhere).

Our Reporting

We take great pains to ensure that the articles, video and graphics you see on Credit.com are thoroughly reported and fact-checked. Each story is read by two separate editors, and we adhere to the highest editorial standards. We’re not perfect, however, and if you see something that you think is wrong, please email us at editorial team [at] credit [dot] com,

The Credit.com editorial team is committed to providing our readers and viewers with sound, well-reported and understandable information designed to inform and empower. We won’t tell you what to do. We will, however, do our best to explain the consequences of various actions, thereby arming you with the information you need to make decisions that are in your best interests. We also write about things relating to money and finance we think are interesting and want to share.

In addition to appearing on Credit.com, our articles are syndicated to dozens of other news sites. We have more than 100 partners, including MSN, ABC News, CBS News, Yahoo, Marketwatch, Scripps, Money Magazine and many others. This network operates similarly to the Associated Press or Reuters, except we focus almost exclusively on issues relating to personal finance. These are not advertorial or paid placements, rather we provide these articles to our partners in most cases for free. These relationships create more awareness of Credit.com in general and they result in more traffic to us as well.

Our Business Model

Credit.com’s journalism is largely supported by an e-commerce business model. Rather than rely on revenue from display ad impressions, Credit.com maintains a financial marketplace separate from its editorial pages. When someone navigates to those pages, and applies for a credit card, for example, Credit.com will get paid what is essentially a finder’s fee if that person ends up getting the card. That doesn’t mean, however, that our editorial decisions are informed by the products available in our marketplace. The editorial team chooses what to write about and how to write about it independently of the decisions and priorities of the business side of the company. In fact, we maintain a strict and important firewall between the editorial and business departments. Our mission as journalists is to serve the reader, not the advertiser. In that sense, we are no different from any other news organization that is supported by ad revenue.

Visitors to Credit.com are also able to register for a free Credit.com account, which gives them access to a tool called The Credit Report Card. This tool provides users with two free credit scores and a breakdown of the information in their Experian credit report, updated twice monthly. Again, this tool is entirely free, and we mention that frequently in our articles, because we think that it’s a good thing for users to have access to data like this. Separate from its educational value, there is also a business angle to the Credit Report Card. Registered users can be matched with products and services for which they are most likely to qualify. In other words, if you register and you find that your credit is less than stellar, Credit.com won’t recommend a high-end platinum credit card that requires an excellent credit score You’d likely get rejected, and that’s no good for you or Credit.com. You’d be no closer to getting a product you need, there’d be a wasted inquiry on your credit report, and Credit.com wouldn’t get paid. These are essentially what are commonly referred to as "targeted ads" in the world of the Internet. Despite all of this, however, even if you never apply for any product, the Credit Report Card will remain free, and none of this will impact how the editorial team reports on credit and credit scores.

Your Stories

Lastly, much of what we do is informed by our own experiences as well as the experiences of our readers. We want to tell your stories if you’re interested in sharing them. Please email us at story ideas [at] credit [dot] com with ideas or visit us on Facebook or Twitter.

Thanks for stopping by.

- The Credit.com Editorial Team