Security and High-Availability While Upholding Network Defense Patterns: The Advantages of A2C in O-RAN VNF Placement
Bibliographic record
Abstract
Next-generation radio access networks such as the Open Radio Access Network (O-RAN) have alleviated many of the 5G demand and management challenges. However, 0-RAN's intelligence, openness, and virtualization have signifi-cantly increased the attack surface of RAN s. This is specifically dangerous for critical 5G use cases such as Ultra-Reliable and Low-latency Communications (URLLC) due to its strict latency and reliability constraints. In this work, we focus on enhancing the security of the data streams and the security of the ML training and inference hosts in O-RAN URLLC deployments by introducing additional network security functions to 0- RAN's service function chains. Our goal is to maximize the amount of traffic examined by the security functions while adhering to 0- RAN's operational and functional constraints and upholding network defense patterns. Two security function types, encryption Virtualized Network Functions (VNFs) and intrusion detection system VNFs are chosen to achieve this objective. Encryption VNFs provide an additional layer of encryption for data traffic, while IDS VNFs protect the ML training and inference hosts of our solution. To solve this complex task, an advantage actor-critic deep reinforcement learning agent is developed, which actively allows adaptation to dynamic traffic. We demonstrate that our solution is capable of increasing the number of security functions in URLLC deployments allowing increased data protection and securing its own training and inference hosts.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".