Federated Multiobjective Convolution Neural Network Architecture for Enabling Efficient Iterative Intrusion Detection Mechanism to the Cloud Services
Bibliographic record
Abstract
Cloud environment and its paradigms are exploring in large extent and revolutionizing the various industries and common peoples with multiple dynamic features and identical functionalities to gain significant prominence. Regardless of its numerous benefits, cloud providers suffers from the security challenges due to digital extortions. Particularly many solutions has been employed using machine learning approaches to detect intrusion and cryptographic techniques for privacy preserving of the cloud user but still many challenges exist due to abnormal activities of the attackers by injecting the large attack vector. In order to mitigate those challenges, a new federated deep learning architecture entitled as federated multi-objective convolution neural network architecture is proposed in this article. It is highly capable of handling large attack variant and its vectors along managing the data privacy challenges of the user information. In this work, Cloud Intrusion Detection Dataset which contain the knowledge and behaviour based audit data collected from the cloud user in real time and CIC-IDS2018 dataset is extracted from the Canadian Institute of Cybersecurity which incorporate data traffic to the cloud services. Initially these dataset were preprocessed through Z-score normalization method for data outlier reduction and data normalization. Preprocessed data is employed to particle swarm optimization which is considered as feature selection method to determine the optimal features for anomaly detection. Selected Optimal feature is employed to multi-objective convolution neural network to detect and classify the multiple attack propagating to the cloud server. Convolution Neural Network generate the feature map for various attacks characteristics which is computed as features in convolution and max pooling layer. Further those feature map is classified in fully connected network using softmax function. Experimental analysis of the proposed architecture is carried out on mentioned dataset to identify the significance of the proposed approach in resource utilization and processing time and performance analysis of the proposed model outperform other state of art architecture on the cross fold validation. Finally current architecture achieves 98.9 percent accuracy on basis of the cloud security.
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 | 0.000 |
| 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 | 0.000 |
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".