Endpoint //

Privacy

3/26/2018
01:10 PM
50%
50%

Facebook Adds Machine Learning to Fraud Fight

Machine learning tools will assist trained human reviewers who Facebook says block millions of fake accounts at the time of registration every day.

In the giant news shadow created by Cambridge Analytics, it can be easy to forget that Facebook-based basic financial fraud victimizes thousands of people every year. Today, Facebook announced that it is enlisting machine learning tools to help battle the criminals.

The new tools will be largely tasked with fighting fake accounts used to commit fraud. While there are a number of techniques being used to identify fraudulent accounts, in a blog post Facebook wrote that the company looks for "instances where people are reaching out to others far beyond their typical network of connections, or in unusually large volumes, along with other behavior patterns."

Facebook's fight against fraud comes against a backdrop of concern about how the social media company treats customers and their data as a general matter. In a statement released today, Tom Pahl, acting director of the Federal Trade Commission’s Bureau of Consumer Protection, says in part, "... the FTC takes very seriously recent press reports raising substantial concerns about the privacy practices of Facebook. Today, the FTC is confirming that it has an open non-public investigation into these practices.”

Machine learning tools will assist trained human reviewers who, Facebook says, block millions of fake accounts at the time of registration every day. In addition, Facebook provides users with a guide to spotting scams and fraud.

For more, read here and here.

Interop ITX 2018

Join Dark Reading LIVE for a two-day Cybersecurity Crash Course at Interop ITX. Learn from the industry’s most knowledgeable IT security experts. Check out the agenda here. Register with Promo Code DR200 and save $200.

Dark Reading's Quick Hits delivers a brief synopsis and summary of the significance of breaking news events. For more information from the original source of the news item, please follow the link provided in this article. View Full Bio

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
White House Cybersecurity Strategy at a Crossroads
Kelly Jackson Higgins, Executive Editor at Dark Reading,  7/17/2018
Mueller Probe Yields Hacking Indictments for 12 Russian Military Officers
Kelly Jackson Higgins, Executive Editor at Dark Reading,  7/13/2018
10 Ways to Protect Protocols That Aren't DNS
Curtis Franklin Jr., Senior Editor at Dark Reading,  7/16/2018
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Write a Caption, Win a Starbucks Card! Click Here
Latest Comment: This comment is waiting for review by our moderators.
Current Issue
Flash Poll
New Best Practices for Secure App Development
New Best Practices for Secure App Development
The transition from DevOps to SecDevOps is combining with the move toward cloud computing to create new challenges - and new opportunities - for the information security team. Download this report, to learn about the new best practices for secure application development.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2018-10869
PUBLISHED: 2018-07-19
redhat-certification does not properly restrict files that can be download through the /download page. A remote attacker may download any file accessible by the user running httpd.
CVE-2018-10870
PUBLISHED: 2018-07-19
redhat-certification does not properly sanitize paths in rhcertStore.py:__saveResultsFile. A remote attacker could use this flaw to overwrite any file, potentially gaining remote code execution.
CVE-2018-12959
PUBLISHED: 2018-07-19
The approveAndCall function of a smart contract implementation for Aditus (ADI), an Ethereum ERC20 token, allows attackers to steal assets (e.g., transfer all contract balances into their account).
CVE-2018-14336
PUBLISHED: 2018-07-19
TP-Link WR840N devices allow remote attackers to cause a denial of service (connectivity loss) via a series of packets with random MAC addresses.
CVE-2018-10620
PUBLISHED: 2018-07-19
AVEVA InduSoft Web Studio v8.1 and v8.1SP1, and InTouch Machine Edition v2017 8.1 and v2017 8.1 SP1 a remote user could send a carefully crafted packet to exploit a stack-based buffer overflow vulnerability during tag, alarm, or event related actions such as read and write, with potential for code t...