# 13o-bbr-bbq/machine_learning_security

Source code about machine learning and security.

Repository: https://github.com/13o-bbr-bbq/machine_learning_security
Canonical: https://ross.abutalabs.com/products/machine_learning_security
Language: Python
License Family: other
Last push: 2026-05-07T08:04:41+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 81, release rhythm 35, longevity 100
- inputs: {"age_days": 3411, "days_push": 118, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2088, forks 676 (observed 2026-08-28T04:06:12.110231+00:00)

## What it is
A collection of Python source code and educational materials combining machine learning with cybersecurity, including a training course for security engineers and tools like Deep Exploit (automated penetration testing), SAIVS (AI vulnerability scanner), and adversarial example generators. It serves as both a learning resource and a set of experimental security tools presented at Black Hat and DEF CON.

## Use cases
- learn machine learning fundamentals as a security engineer
- run automated penetration testing with machine learning
- generate adversarial examples against CNNs
- analyze packet capture data with k-means clustering
- scan web applications for vulnerabilities using AI
- generate injection codes for web app assessment
- recommend optimal injection codes for vulnerability detection

## When to choose
- you want to study the intersection of ML and offensive security
- you need reference implementations of ML-driven pentest tools
- you're building AI-based vulnerability scanners or exploit generators
- you want a structured ML course tailored for security engineers

## When to avoid
- you need a production-ready, maintained security product with a license
- you want defensive ML security tooling rather than offensive testing
- you need polished software with documentation and support
- you're not comfortable with experimental research-grade code

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, penetration-testing, vulnerability-scanning, security, deep-learning
- domain: security, penetration-testing, machine-learning, artificial-intelligence, developer-tools
- platform: python, cli
- tags: adversarial-examples, pentesting, adversarial-machine-learning, vulnerability-scanner, security-course, exploit-generation, linux

## Member repositories
- 13o-bbr-bbq/machine_learning_security (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:12.110231+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:55:40.583674+00:00, confidence not recorded.
  - readme: https://github.com/13o-bbr-bbq/machine_learning_security (fetched 2026-08-28T04:06:12.110231+00:00, sha a23ff7f62e29)
- Data as of 2026-08-30T08:39:29.467469+00:00.