Threat Intelligence

12/14/2018
09:15 AM
50%
50%

Cybercriminals Change Tactics to Outwit Machine-Learning Defense

The rise in machine learning for security has forced criminals to rethink how to avoid detection.

Cybercriminals know that defenders have begun using machine learning to keep users safe. In response, they are changing their tactics to outwit the defenses, and machine learning that leans heavily on historic loss patterns is especially vulnerable.

According to the "Q3 2018 DataVisor Fraud Index Report," which is based on an analysis of sample data from more than 40 billion events, fraud actors have changed their tools so that they can quickly adapt to new defenses put in place by companies. In a statement accompanying the report, DataVisor puts numbers to the quick adaptation, saying, "Out of the fraud signals detected, 36% were active for less than one day, and 64% for less than one week."

In addition, sophisticated fraud actors are now more likely to make use of private domains, conduct multilayer, staged attacks, and wait for days or weeks between those stages.

Read more details here.

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
Crowdsourced vs. Traditional Pen Testing
Alex Haynes, Chief Information Security Officer, CDL,  3/19/2019
BEC Scammer Pleads Guilty
Dark Reading Staff 3/20/2019
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
5 Emerging Cyber Threats to Watch for in 2019
Online attackers are constantly developing new, innovative ways to break into the enterprise. This Dark Reading Tech Digest gives an in-depth look at five emerging attack trends and exploits your security team should look out for, along with helpful recommendations on how you can prevent your organization from falling victim.
Flash Poll
The State of Cyber Security Incident Response
The State of Cyber Security Incident Response
Organizations are responding to new threats with new processes for detecting and mitigating them. Here's a look at how the discipline of incident response is evolving.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2019-10014
PUBLISHED: 2019-03-24
In DedeCMS 5.7SP2, member/resetpassword.php allows remote authenticated users to reset the passwords of arbitrary users via a modified id parameter, because the key parameter is not properly validated.
CVE-2019-10015
PUBLISHED: 2019-03-24
baigoStudio baigoSSO v3.0.1 allows remote attackers to execute arbitrary PHP code via the first form field of a configuration screen, because this code is written to the BG_SITE_NAME field in the opt_base.inc.php file.
CVE-2019-10017
PUBLISHED: 2019-03-24
CMS Made Simple 2.2.10 has XSS via the advanced_search.php Name field, which is reachable via an "Add a new Profile" action to the File Picker.
CVE-2019-10010
PUBLISHED: 2019-03-24
Cross-site scripting (XSS) vulnerability in the PHP League CommonMark library before 0.18.3 allows remote attackers to insert unsafe links into HTML by using double-encoded HTML entities that are not properly escaped during rendering, a different vulnerability than CVE-2018-20583.
CVE-2019-9978
PUBLISHED: 2019-03-24
The social-warfare plugin before 3.5.3 for WordPress has stored XSS via the wp-admin/admin-post.php?swp_debug=load_options swp_url parameter, as exploited in the wild in March 2019. This affects Social Warfare and Social Warfare Pro.