Pwnagotchi is an A2C-based “AI” powered by bettercap and running on a Raspberry Pi Zero W that learns from its surrounding WiFi environment in order to maximize the crackable WPA key material it captures (either through passive sniffing or by performing deauthentication and association attacks). This material is collected on disk as PCAP files containing any form of handshake supported by hashcat, including full and half WPA handshakes as well as PMKIDs. Instead of merely playing Super Mario or Atari games like most reinforcement learning based “AI” (yawn), Pwnagotchi tunes its own parameters over time to get better at pwning WiFi things in the real world environments you expose it to. To give hackers an excuse to learn about reinforcement learning and WiFi networking, and have a reason to get out for more walks.
Features
- Your unit can operate in one of three different “modes” that determines how it behaves
- If connected to the USB data port of your computer (or a tablet, phone, etc), your Pwnagotchi will start in MANUAL mode
- In MANU mode, you’ll be able to access bettercap’s web UI from your computer
- In AUTO mode, your unit will start operating, perform attacks and sniffing handshakes
- If AI is enabled in your configuration (as it is by default), AUTO mode will transition to AI mode after a few minutes
- Pwnagotchi’s face, otherwise known as the UI, is available at a dedicated web interface
Project Samples
