Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Unsupervised, low latency anomaly detection of algorithmically generated domain names by generative probabilistic

Jayaram Raghuram1, David J Miller1, George Kesidis2

  • 1Department of Electrical Engineering, Pennsylvania State University, University Park, PA 16802, USA.

Journal of Advanced Research
|February 17, 2015
PubMed
Summary

Related Concept Videos

Detection of Black Holes01:10

Detection of Black Holes

2.6K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Modernizing Pesticide Risk Assessment: Technical Advancements as the Path toward Global Food Security.

Journal of agricultural and food chemistry·2026
Same author

Sperm-female interactions in the pig oviduct, a key for insemination success?

The Journal of reproduction and development·2026
Same author

Designed Water Capture in Terpene Synthase Catalysis.

Chembiochem : a European journal of chemical biology·2026
Same author

Microbial Metabolism and Disease Virulence Changes Across Day and Night in Coral Black Band Disease Lesions.

Environmental microbiology·2026
Same author

Major transitions in early coral development: novel insights enabled by visualisation of a comprehensive transcriptomic dataset for Acropora millepora.

BMC biology·2026
Same author

U.S. Leadership in Food Safety: A Blueprint for Global Food Security through Pesticide Science.

Journal of agricultural and food chemistry·2025
This summary is machine-generated.

This study introduces a new method to detect malicious, algorithmically generated domain names. By modeling normal domain name patterns, it effectively identifies anomalous names linked to botnets and phishing with high accuracy.

Area of Science:

  • Cybersecurity
  • Machine Learning
  • Network Security

Background:

  • Algorithmically generated domain names are frequently used for malicious activities like botnets, malware, and phishing.
  • Existing detection methods often rely on additional, latency-inducing information sources.
  • Human-assigned domain names exhibit linguistic characteristics (pronounceability, word distribution) distinct from machine-generated ones.

Purpose of the Study:

  • To develop a novel method for detecting anomalous domain names, specifically focusing on algorithmically generated ones.
  • To create a probability model for benign, human-assigned domain names to serve as a baseline for anomaly detection.
  • To identify malicious domain names without requiring supplementary data sources.

Main Methods:

Keywords:
Algorithmically generated domain namesAnomaly detectionDomain name modelingFast fluxMalicious domain names

Related Experiment Videos

  • Learning a probability model from a large dataset of white-listed, human-assigned domain names.
  • Utilizing a fully generative model to capture the distribution of benign domain names.
  • Applying anomaly detection techniques to identify deviations from the learned benign model.

    • Main Results:

    • The proposed method demonstrated encouraging results on a large dataset of fast flux domain names.
    • Achieved higher detection rates compared to several baseline methods.
    • Maintained low false positive rates in identifying anomalous domain names.

    Conclusions:

    • The generative probability model effectively distinguishes between human-created and algorithmically generated domain names.
    • The method provides an efficient way to detect malicious domain names associated with fast flux networks.
    • This approach offers a promising alternative for cybersecurity threat detection without added latency.