Jump to content

User behavior analytics: Difference between revisions

From Wikipedia, the free encyclopedia
Content deleted Content added
No edit summary
No edit summary
Tag: Reverted
Line 8: Line 8:
<!-- Section is bare & consists of quote only. Please fix! -->
<!-- Section is bare & consists of quote only. Please fix! -->
</ref>
</ref>

== Research ==
The current [https://arxiv.org/abs/2111.13176 state of the art]<ref>{{Citation
| last1 = Khanna
| first1 = Sameer
| title = Computer Vision User Entity Behavior Analytics
| publisher = arXiv
| year = 2021
| id = (2111.13176)
| url = https://arxiv.org/abs/2111.13176
}}</ref> encodes user behavior as color image encodings designed to compare against baseline behavior, using pre-trained computer vision architectures to identify anomalous behavior with malicious intent rather than detecting particular attack patterns. This approach outperforms alternatives while also mitigating many of the concerns mentioned in the previous section.


==See also==
==See also==

Revision as of 05:25, 7 December 2021

User behavior analytics (UBA) is a cybersecurity process about detection of insider threats, targeted attacks, and financial fraud that tracks a system's users. UBA looks at patterns of human behavior, and then analyzes them to detect anomalies that indicate potential threats.[1][2] Big data platforms like Apache Hadoop are increasing UBA functionality by allowing them to analyze petabytes worth of data to detect insider threats and advanced persistent threats.[3][4]

Purpose

UBA's purpose, according to Johna Till Johnson of Nemertes Research, is that "Security systems provide so much information that it's tough to uncover information that truly indicates a potential for real attack. Analytics tools help make sense of the vast amount of data that SIEM, IDS/IPS, system logs, and other tools gather. UBA tools use a specialized type of security analytics that focuses on the behavior of systems and the people using them. UBA technology first evolved in the field of marketing, to help companies understand and predict consumer-buying patterns. But as it turns out, UBA can be extraordinarily useful in the security context too."[5]

Research

The current state of the art[6] encodes user behavior as color image encodings designed to compare against baseline behavior, using pre-trained computer vision architectures to identify anomalous behavior with malicious intent rather than detecting particular attack patterns. This approach outperforms alternatives while also mitigating many of the concerns mentioned in the previous section.

See also

References

  1. ^ Market Guide for User Behavior Analytics
  2. ^ The hunt for data analytics: Is your SIEM on the endangered list?
  3. ^ Ahlm, Eric; Litan, Avivah (26 April 2016). "Market Trends: User and Entity Behavior Analytics Expand Their Market Reach". Gartner. Retrieved 15 July 2016.
  4. ^ "Cybersecurity at petabyte scale". Retrieved 15 July 2016.
  5. ^ User behavioral analytics tools can thwart security attacks
  6. ^ Khanna, Sameer (2021), Computer Vision User Entity Behavior Analytics, arXiv, (2111.13176)