cage-challenge-4
Network defender
Developing an AI system to protect a network against cyber threats in a simulated environment
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 enterprise environment, and introduces a Multi-Agent Reinforcement Learning (MARL) scenario.
42 stars
4 watching
10 forks
Language: Python
last commit: about 1 year ago cybersecuritymultiagent-reinforcement-learningreinforcement-learning
Related projects:
| Repository | Description | Stars |
|---|---|---|
| cage-challenge/cage-challenge-2 | An AI research challenge and platform to test autonomous cyber defense capabilities using a simulated environment. | 46 |
| cage-challenge/cage-challenge-1 | A challenge to develop AI-based solutions for autonomous cyber operations in a controlled environment. | 51 |
| cage-challenge/cage-challenge-3 | A reinforcement learning challenge where participants are invited to solve an open-ended problem using various approaches. | 34 |
| cage-challenge/cyborg | A cyber security research environment for training and development of security human and autonomous agents. | 65 |
 niklasb/35c3ctf-challs | A collection of cryptographic and coding challenges designed to test problem-solving skills | 88 |
 center-for-threat-informed-defense/adversary_emulation_library | Provides a collection of plans to test defenses against real-world cyber threats. | 1,737 |
 kaixhin/malmo-challenge | An AI project that aims to develop an agent that can navigate and interact with a Minecraft environment while learning from its opponents' strategies | 65 |
 kanadaat/aoc2023 | Solutions to Advent of Code challenges in C# | 0 |
 cylance/introductiontomachinelearningforsecuritypros | A collection of examples and code snippets teaching machine learning concepts to security professionals through hands-on Python projects | 151 |
 kudelskisecurity/cryptochallenge18 | A cryptographic challenge with three stages, requiring participants to solve digital signature and decryption problems within a limited timeframe. | 36 |
 eth-sri/diffai | Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques. | 219 |
 git-disl/lockdown | A backdoor defense system for federated learning, designed to protect against data poisoning attacks by isolating subspace training and aggregating models with robust consensus fusion. | 18 |
 rhinosecuritylabs/ccat | A tool designed to test the security of container environments by simulating various attacks and vulnerabilities. | 595 |
 cider-security-research/cicd-goat | A deliberately vulnerable CI/CD environment designed to teach security best practices through interactive challenges | 1,967 |
 team0se7en/ctf-writeups | A collection of writeups on solving Capture The Flag challenges using Python. | 15 |