# Kayzaks/HackingNeuralNetworks

A small course on exploiting and defending neural networks

Repository: https://github.com/Kayzaks/HackingNeuralNetworks
Canonical: https://ross.abutalabs.com/products/hackingneuralnetworks
Language: Python
License: MIT
License Family: permissive
Last push: 2020-02-29T02:16:13+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2514, "days_push": 2378, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2635, forks 304 (observed 2026-08-28T04:07:06.233556+00:00)

## What it is
A short educational course (article plus Python exercises) on attacking and defending neural networks, covering techniques like backdooring, information extraction, malware injection, and bug hunting. It is built with Keras/TensorFlow and accompanies an arXiv paper.

## Use cases
- learn how to exploit neural networks
- study adversarial machine learning attacks
- practice backdooring and model extraction exercises
- learn to defend models against malware injection
- explore using neural networks for offensive security tasks
- find a hands-on intro to hacking ML systems

## When to choose
- you want a hands-on, exercise-driven introduction to offensive and defensive ML
- you are comfortable with Python, Keras, and TensorFlow
- you want a short course backed by an arXiv paper

## When to avoid
- you need production-ready attack or defense tooling
- you need actively maintained code with recent updates
- you are looking for a general deep learning tutorial rather than security-focused content

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, security, penetration-testing, nlp, computer-vision
- domain: security, machine-learning, deep-learning, tutorials, artificial-intelligence
- platform: python, cross-platform
- tags: adversarial-attacks, offensive-ml, neural-network-security, educational-course, exercises, keras, tensorflow

## Member repositories
- Kayzaks/HackingNeuralNetworks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.233556+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 2026-08-30T02:19:20.159825+00:00, confidence not recorded.
  - readme: https://github.com/Kayzaks/HackingNeuralNetworks (fetched 2026-08-28T04:07:06.233556+00:00, sha c07b04f90d6d)
- Data as of 2026-08-30T08:39:29.467469+00:00.