FOE-Dreamer: Deployment-Efficient Learning of Cyber Defense Policies in Operational Networks
cs.LG, cs.CR
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/microsoft/CyberBattleSim
Terminology
Sources
- SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
- CybORG: A Gym for the Development of Autonomous Cyber Agents
- Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
- Developing Optimal Causal Cyber-Defence Agents via Cyber Security Simulation
- Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems
- Opponent Modeling in Deep Reinforcement Learning
- Learning Policy Representations in Multiagent Systems
- Machine Theory of Mind
- Agent Modelling under Partial Observability for Deep Reinforcement Learning
- Recurrent World Models Facilitate Policy Evolution
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Atari with Discrete World Models
- Mastering Diverse Domains through World Models
- The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning
- CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems
- Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense
- Quantifying Generalization in Reinforcement Learning
- Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks
- Learning Near-Optimal Intrusion Responses Against Dynamic Attackers
- Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis