scifijunkie/pwnagotchi
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

misc: small fix or general refactoring i did not bother commenting

Browse Source
This commit is contained in:
Simone Margaritelli 2019-10-15 13:19:30 +02:00
parent aa60a369a9
commit ee3fb285be
No known key found for this signature in database
GPG Key ID: 82E42E7F3B34C97E
1 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -14,7 +14,7 @@
[Pwnagotchi](https://pwnagotchi.ai/) is an [A2C](https://hackernoon.com/intuitive-rl-intro-to-advantage-actor-critic-a2c-4ff545978752)-based "AI" leveraging [bettercap](https://www.bettercap.org/) that learns from its surrounding WiFi environment to maximize the crackable WPA key material it captures (either passively, or by performing authentication and association attacks). This material is collected as PCAP files containing any form of handshake supported by [hashcat](https://hashcat.net/hashcat/), including [PMKIDs](https://www.evilsocket.net/2019/02/13/Pwning-WiFi-networks-with-bettercap-and-the-PMKID-client-less-attack/),
full and half WPA handshakes.
![alpha](https://media.giphy.com/media/f9GsXyfgEQbY65fnhu/source.gif)
![ui](https://i.imgur.com/c7xh4hN.png)
Instead of merely playing [Super Mario or Atari games](https://becominghuman.ai/getting-mario-back-into-the-gym-setting-up-super-mario-bros-in-openais-gym-8e39a96c1e41?gi=c4b66c3d5ced) like most reinforcement learning-based "AI" *(yawn)*, Pwnagotchi tunes [its parameters](https://github.com/evilsocket/pwnagotchi/blob/master/pwnagotchi/defaults.yml#L73) over time to **get better at pwning WiFi things to** in the environments you expose it to.
@ -22,8 +22,6 @@ More specifically, Pwnagotchi is using an [LSTM with MLP feature extractor](http
**Keep in mind:** Unlike the usual RL simulations, Pwnagotchi learns over time. Time for a Pwnagotchi is measured in epochs; a single epoch can last from a few seconds to minutes, depending on how many access points and client stations are visible. Do not expect your Pwnagotchi to perform amazingly well at the very beginning, as it will be [exploring](https://hackernoon.com/intuitive-rl-intro-to-advantage-actor-critic-a2c-4ff545978752) several combinations of [key parameters](https://www.pwnagotchi.ai/usage/#training-the-ai) to determine ideal adjustments for pwning the particular environment you are exposing it to during its beginning epochs ... but ** listen to your Pwnagotchi when it tells you it's boring!** Bring it into novel WiFi environments with you and have it observe new networks and capture new handshakes—and you'll see. :)
![ui](https://i.imgur.com/c7xh4hN.png)
Multiple units within close physical proximity can "talk" to each other, advertising their presence to each other by broadcasting custom information elements using a parasite protocol I've built on top of the existing dot11 standard. Over time, two or more units trained together will learn to cooperate upon detecting each other's presence by dividing the available channels among them for optimal pwnage.
## Documentation