Endpoint

11/7/2017
11:19 AM
Dark Reading
Dark Reading
Products and Releases
50%
50%

Shape Security Releases AI System to Prevent Use of Compromised Credentials

Shape Security introduces Blackfish artificial intelligence system to protect consumers whose passwords have been stolen in data breaches. New technology detects and prevents the use of compromised credentials even when data breaches are undiscovered or undisclosed.

MOUNTAIN VIEW, Calif., Nov. 07, 2017 (GLOBE NEWSWIRE) -- Shape Security, a provider of advanced security and fraud technology for the world’s largest companies, today launched Blackfish, the first system that can autonomously identify passwords stolen from a data breach before the data breach is reported or even detected. With this technology, organizations worldwide can eliminate the use of stolen usernames and passwords by identifying compromised credentials used to take over accounts, months or even years before the credentials show up for sale on the dark web. Blackfish is built upon the Shape global network, which is the primary line of application defense for the world’s leading companies, including three of the top four banks, three of the top five airlines, two of the top five hotel chains, and two of the top five U.S. government agencies.

Credential stuffing attacks are responsible for more than $10 billion in fraud losses, identify theft, and brand damage every year. Shape’s network data shows that in many industries, such as retail, more than 90% of all login attempts to websites often come from credential stuffing attacks instead of from real users. In these attacks, cybercriminals use advanced automation to test stolen passwords on other websites, simulating real users to take over large groups of accounts en masse.

“One of the greatest dangers companies face today is the long window of time between when breaches occur on third-party websites like Yahoo, and when those breaches are discovered and announced. This puts users everywhere at risk,” said Derek Smith, CEO of Shape Security. “Blackfish changes this entirely. By automatically detecting credential stuffing attacks on the largest, most targeted websites in the world, we are able to quickly identify newly stolen credentials and nullify them globally. That stolen data becomes useless to cybercriminals.”

Shape’s Blackfish technology will enable a unique defense across its customer network, which represents the largest companies in the industries most targeted by cybercriminals. Blackfish machine learning sensors analyze hundreds of signals in login attempts on major websites to automatically identify credentials being used by anyone other than their rightful owners. It then protects all other sites against account takeover attempts which use those credentials.

To ensure that its knowledge base is secured, Blackfish does not store any credential information but instead leverages Bloom filters to create probabilistic data structures to perform its operations. As a result, the compromised credentials themselves are not stored anywhere and Blackfish can use the information about compromises to improve security while maintaining full data privacy.

“In June, the National Institute of Standards and Technology (NIST) issued the recommendation that all companies check their users’ credentials against breached password corpuses,” said Sarah Squire, co-author of the NIST Digital Identity Guidelines (SP 800-63). "Shape is going one step further by enabling companies to cross-reference with a breach corpus that is actively exploited and not dependent on companies self-disclosing breaches in a timely manner.”

“The problem of credential stuffing cannot be fully solved without dealing with the stolen passwords themselves,” said Ted Schlein, General Partner at Kleiner Perkins. “Blackfish is the first technology that can identify compromised credentials before a data breach is discovered and ensure that cybercriminals cannot use them. The Blackfish system is also a strong demonstration of the power of Shape's network data, from protecting the world's largest organizations to providing a new level of defense for companies and their users.”

To learn more, visit: https://shapesecurity.com/blackfish.

About Shape Security
The world’s leading financial, retail and travel companies and government agencies rely on Shape Security as their primary line of defense against fraud and attacks on their web and mobile applications. The Shape platform, covered by 45 patents, was designed to stop the most dangerous application attacks enabled by cybercriminal fraud tools, including credential stuffing (account takeover), product scraping, unauthorized aggregation, and other threats. Shape has prevented over $1 billion in fraud losses for its customers and protects more than 1.3 billion user accounts. Shape is headed by industry leaders from Google, Cisco, IBM, Raytheon, Palo Alto Networks, and the Pentagon.

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
Election Websites, Back-End Systems Most at Risk of Cyberattack in Midterms
Kelly Jackson Higgins, Executive Editor at Dark Reading,  8/14/2018
Intel Reveals New Spectre-Like Vulnerability
Curtis Franklin Jr., Senior Editor at Dark Reading,  8/15/2018
Data Privacy Careers Are Helping to Close the IT Gender Gap
Dana Simberkoff, Chief Compliance and Risk Management Officer, AvePoint, Inc,  8/20/2018
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
Flash Poll
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2018-15601
PUBLISHED: 2018-08-21
apps/filemanager/handlers/upload/drop.php in Elefant CMS 2.0.3 performs a urldecode step too late in the "Cannot upload executable files" protection mechanism.
CVE-2018-15603
PUBLISHED: 2018-08-21
An issue was discovered in Victor CMS through 2018-05-10. There is XSS via the Author field of the "Leave a Comment" screen.
CVE-2018-15598
PUBLISHED: 2018-08-21
Containous Traefik 1.6.x before 1.6.6, when --api is used, exposes the configuration and secret if authentication is missing and the API's port is publicly reachable.
CVE-2018-15599
PUBLISHED: 2018-08-21
The recv_msg_userauth_request function in svr-auth.c in Dropbear through 2018.76 is prone to a user enumeration vulnerability because username validity affects how fields in SSH_MSG_USERAUTH messages are handled, a similar issue to CVE-2018-15473 in an unrelated codebase.
CVE-2018-0501
PUBLISHED: 2018-08-21
The mirror:// method implementation in Advanced Package Tool (APT) 1.6.x before 1.6.4 and 1.7.x before 1.7.0~alpha3 mishandles gpg signature verification for the InRelease file of a fallback mirror, aka mirrorfail.