cage-challenge-4 icon indicating copy to clipboard operation
cage-challenge-4 copied to clipboard

The TTCP CAGE Challenges are a series of public challenges instigated to foster the development of autonomous cyber defensive agents. This CAGE Challenge 4 (CC4) returns to a defence industry enterpri...

Results 13 cage-challenge-4 issues
Sort by recently updated
recently updated
newest added

There are a few places where TernaryEnums are used in a Boolean context. Currently these are badly broken. This allows red agents to get a ton of Impact points incorrectly....

## Description Currently when `pad_spaces` is set, action spaces are padded out to be the same size across all agents. However, this is done by simply appending enough `[Padding] Sleep()`...

I have noticed that red shell sessions that are created as a result of phishing e-mails do not appear to have any files associated with them. This means they are...

By adding actions from the default agents back to the `actions` object, any action with associated cost (i.e. `Restore`), will be correctly penalized during reward calculation. This fixes issue #40.

Having the ability to search the documentation would be very helpful. This PR makes use of the search plugin from `mkdocs-material`. More info can be found here: https://squidfunk.github.io/mkdocs-material/setup/setting-up-site-search/

Tiny issue, but the constructor for `AllowTrafficZone` is written as `def __init__(self, session: int, agent: str, from_subnet: str, to_subnet: IPv4Network):` when it should be `def __init__(self, session: int, agent: str,...

I noted that the phishing mails were "sent" to operational even if it was on a phase where operational couldn't be joined. It past throught the BlockTrafficZone action also. This...

Small documentation issue, in the visualisation tutorial, the VisualiseRedExpansion class is in CybORG.Agents.Wrappers.VisualiseRedExpansion and not in CybORG.render.visualisation.VisualiseRedExpansion (wich does not exist in this version of Cyborg)

documentation

Updates the action padding method to intersperse the padding between different action types (e.g. between Analyse and Monitor and between Monitor and Remove) so that when using padding, action 145...

A few things about the management of RNGs seem wrong to me. I would have assumed that `CybORG.set_seed()` could be used to re-seed the simulation. But references to the RNG...