An AI-powered WiFi security auditing tool that uses deep reinforcement learning to optimize capture of WPA handshakes.
Pwnagotchi is an AI-powered WiFi security auditing tool that uses deep reinforcement learning to optimize the capture of WPA handshakes and other crackable key material. It leverages bettercap to interact with WiFi networks, learning from its environment to improve its effectiveness over time. The system adapts its parameters based on the networks it encounters, making it a dynamic tool for wireless penetration testing.
Security researchers, penetration testers, and WiFi auditing enthusiasts who want an automated, learning-based approach to capturing WPA handshakes for security assessments.
Unlike static WiFi auditing tools, Pwnagotchi continuously learns and adapts to its environment, improving its efficiency over time. Its use of reinforcement learning and ability for multiple units to cooperate makes it uniquely capable for evolving wireless security testing scenarios.
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Uses an A2C agent with LSTM and MLP to continuously tune parameters, improving handshake capture efficiency over time as it learns from specific WiFi environments, as described in the README's emphasis on learning through epochs.
Units communicate via a custom protocol built on dot11 standards, learning to divide channels for optimal efficiency when in proximity, enhancing collaborative auditing capabilities.
Leverages bettercap for both passive and active attacks, capturing various handshake types like PMKIDs and full/half WPA handshakes supported by hashcat, as highlighted in the key features.
Applies reinforcement learning beyond simulations to practical security challenges, making it a unique tool for evolving WiFi auditing, unlike typical game-focused RL projects.
The README admits it does not perform amazingly well at the beginning, requiring exposure to novel environments over epochs to improve, which can be frustrating for quick results.
Requires a Raspberry Pi, compatible WiFi adapter, and configuration with bettercap, involving significant assembly and setup time compared to software-only tools.
Focused on capturing WPA key material for auditing, the documentation lacks strong emphasis on legal use, posing risks for unauthorized testing in regulated environments.