AI-Driven Threat Intelligence Framework for Real-Time Cybersecurity using Federated Deep Learning and Cloud Orchestration
Bibliographic record
Abstract
As cyber risks targeting distributed infrastructures are expanding rapidly, centralized detection methods are becoming problematic on all fronts: scalability, privacy, and latency. The paper introduces a new artificial intelligence-based threat intelligence framework that incorporates federated deep learning and cloud orchestration into the framework to achieve real-time, privacy-preserving cybersecurity. The structure makes use of a hybrid CNN-BiLSTM network plus edge-node attention controls accurate recognition of temporal-spatial attack patterns on small data volumes without releasing sensitive data. FedProx algorithm is used to synchronize the model updates to facilitate heterogeneous data distributions. Cloud orchestration with Kubernetes provides a highly available and elastic distribution of detected nodes, in a fault tolerant manner. On benchmark intrusion detection data sets NSL-KDD and CICIDS2017, the system is evaluated to be 97.8 accurate, outperforming existing centralized and federated models in both communication overhead and detection latency. The method shows that real-time cyber threat intelligence can be addressed with a scalable, secure and robust solution with potential protective implications to both enterprises and critical infrastructures.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".