jivoi/awesome-ml-for-cybersecurity

★ 8,689Audience · researcherComplexity · 1/5Setup · easy

Mindmap

mindmap
  root((ML for Security))
    Datasets
      Intrusion detection
      Malware samples
      Phishing and spam
      Packet captures
    Papers
      PDF malware detection
      Network behavior analysis
      Password modeling
      Anomaly detection
    Learning Resources
      Books
      Video talks
      Courses
      Tutorials
    Audience
      Security researchers
      ML practitioners

mindmap root((ML for Security)) Datasets Intrusion detection Malware samples Phishing and spam Packet captures Papers PDF malware detection Network behavior analysis Password modeling Anomaly detection Learning Resources Books Video talks Courses Tutorials Audience Security researchers ML practitioners

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Find publicly available datasets for training intrusion detection or malware classification models

USE CASE 2

Build a reading list of academic papers before starting a security ML project

USE CASE 3

Discover video talks and university courses on applying ML to cybersecurity

USE CASE 4

Locate phishing, spam, and network capture datasets for research experiments

Getting it running

Difficulty · easy Time to first run · 5min

License not specified in the explanation, check the repository directly before redistributing.

In plain English

This repository is a curated reading list focused on one specific crossover: applying machine learning to cybersecurity problems. It does not contain runnable code. Instead, it is an organized collection of links to datasets, academic papers, books, video talks, tutorials, courses, and miscellaneous tools that researchers and practitioners have found useful in this area. The datasets section lists publicly available data that someone building a security-focused machine learning model might train or test against. These include network intrusion detection datasets, malware samples, spam corpora, phishing data, web attack payloads, and packet capture files from various universities, government labs, and research organizations. The papers section covers academic research on topics like detecting malicious PDF files, identifying malware through network behavior, spotting phishing domains using passive DNS data, password strength modeling with neural networks, and anomaly detection in system logs. Several papers in Russian are also included. The list spans roughly a decade of published work, so some entries are foundational older research and some are more recent. The books, talks, tutorials, and courses sections follow the same pattern: they point outward to external resources rather than providing content directly in this repository. This kind of list is most useful as a starting point for someone who wants to explore the research landscape, find training data for a project, or build a reading list before going deeper into any one area. It is a reference index, not a guide with explanations or commentary on the items listed.

Copy-paste prompts

Prompt 1

List the intrusion detection datasets in this repo and describe what each one contains.

Prompt 2

Which papers in this list cover malware detection using network behavior rather than static analysis?

Prompt 3

I want to start a machine learning project to detect phishing domains, which datasets and papers here should I start with?

Prompt 4

Find me beginner-friendly courses or tutorials from this list that cover ML applied to security.

Prompt 5

Which entries in this list focus on anomaly detection in system logs?

Open on GitHub → Explain another repo

← jivoi on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.