Bibliographic record
Abstract
This work presents the preliminary results of and discusses current challenges in ongoing research of neuroevolution for the task of evolving agents for autonomous cyber operations (ACO). The application of reinforcement learning to the cyber domain is especially challenging due to the extremely limited observability of the environment over extended time frames where an adversary can potentially take many actions without being detected. To promote research within this space The Technical Cooperation Program (TTCP), which is an international collaboration organization between the US, UK, Canada, Australia, and New Zealand, released the Cyber Operations Research Gym (CybORG) to enable experimentation with RL algorithms in both simulated and emulated environments. Using competition to spur investigation and innovation, TTCP has released the CAGE Challenges which for evaluating RL in network defense.[1] This work evolves agents for ACO using the python-based neuroevolution library Evosax[2] which supports high performance, GPU accelerated evolutionary algorithms for the purpose of optimizing artificial neural network parameters. The use of neuroevolution in this paper is a first for the ACO task and benchmarks two popular algorithms to identify factors which impact their effectiveness.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".