Anomaly Detection in Cloud Environments Using Bayesian Networks and Reinforcement Learning
Bibliographic record
Abstract
A significant shift from traditional data centers to multi-cloud systems has transpired due to the emergence of cloud computing as a means for application service providers and corporations to reduce both initial and continuing operational costs. This move enhances scalability, latency, and load balancing, but it also introduces security vulnerabilities, particularly concerning anomaly detection. This research introduces a three-phase anomaly detection system utilizing BN-RL to address these issues. The system functions in the following manner: preprocessing, feature selection, and model training. This work introduces ECOFS, an innovative method for feature removal and the effective management of linear and nonlinear data dependencies. Furthermore, RL and BN collaborate to enhance decision-making precision, enabling the agent to select the optimal course of action from a range of options. The proposed model outperformed prior methods in a cloud environment, with an accuracy of 99.39% in anomaly detection. The BN-RL architecture is proficient in safeguarding cloud-based systems, as evidenced by these findings. The model demonstrates potential in cloud security due to its incorporation of sophisticated feature selection and uncertainty mitigation methods. The scalability and deployment across various cloud infrastructures might be enhanced in future endeavours.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".