Pith. sign in

REVIEW 6 cited by

CybORG: A Gym for the Development of Autonomous Cyber Agents

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2108.09118 v1 pith:TJM5Y23I submitted 2021-08-20 cs.CR

Maxwell Standen , Martin Lucas , David Bowman , Toby J. Richer , Junae Kim , Damian Marriott This is my paper
classification cs.CR
keywords agentsautonomouscyborgcyberdevelopmentteamadversarialalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Autonomous Cyber Operations (ACO) involves the development of blue team (defender) and red team (attacker) decision-making agents in adversarial scenarios. To support the application of machine learning algorithms to solve this problem, and to encourage researchers in this field to attend to problems in the ACO setting, we introduce CybORG, a work-in-progress gym for ACO research. CybORG features a simulation and emulation environment with a common interface to facilitate the rapid training of autonomous agents that can then be tested on real-world systems. Initial testing demonstrates the feasibility of this approach.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. NetForge RL: A Multi-Agent Simulation Environment for Cyber Defense with Durative Actions

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    NetForge RL ships a PettingZoo multi-agent cyber-defense simulator with SIEM/Sysmon embeddings, MITRE ATT&CK actions, JAX vectorization, baselines, diagnostic probes, and seeded evaluation.

  2. Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation

    cs.LG 2025-09 conditional novelty 6.0 of 10

    In stochastic, partially observable simulated networks, PPO with element-wise augmented observation history converges faster and achieves higher reward than PPO with frame stacking, LSTM, or transformer memory.

  3. CyGym: A Simulation-Based Game-Theoretic Analysis Framework for Cybersecurity

    cs.CR 2025-06 conditional novelty 6.0 of 10

    CyGym provides a Gym-based cyber simulation with a POSG formalization, zero-day modeling, and a PSRO-style solver, evaluated on a Volt Typhoon scenario.

  4. Open Security Benchmark: Towards Autonomous Enterprise Cyber Defense

    cs.CR 2026-07 conditional novelty 5.0 of 10

    OSB proposes frozen synthetic-enterprise snapshots with gold posture answers so AI agents can be benchmarked on security investigation via SQL or native vendor APIs.

  5. Evolutionary and Coevolutionary Multi-Agent Design Choices and Dynamics

    cs.NE 2025-07 conditional novelty 5.0 of 10

    In CybORG's CAGE Challenge 4, grammar-evolved controllers outperform matrix-based controllers, and coevolving both sides dampens reward peaks compared to evolving one side against a fixed opponent.

  6. Nash Q-Network for Multi-Agent Cybersecurity Simulation

    cs.MA 2025-08 reject novelty 4.0 of 10

    A MARL variant that trains agents by aligning their policies with Nash equilibria of a centralized critic's joint Q-values, demonstrated on the CybORG CC2 cyber-defense scenario.

Pith tools