Optimizing Malware Detection and Classification in Real-Time Using Hybrid Deep Learning Approaches
Bibliographic record
Abstract
Malware detection and classification are critical for ensuring system security in real-time applications.Conventional approaches may not be optimized to combine precise results with low time consumption and become a problem when it comes to processing large volumes of different malware samples in a real-time setting.The general framework for this paper is to introduce a new detection and classification method that uses deep learning (DL) models to detect and classify malware.We developed and tested two models: the static convolutional neural network-long short-term memory (CNN-LSTM) model and the dynamic CNN 1D-LSTM model in this work.The models achieved an accurate rate of 99%.Static-CNN-LSTM was able to classify the malware based on static analysis.At the same time, the proposed dynamic (1D-CNN-LSTM) model got the best results, with a 100% success rate, by gathering behavioral data.This means that it can accurately classify even new and complicated dynamic malicious program variants.Therefore, this study's results show that using a hybrid approach raises the rate of detection while also meeting the real-time processing needs of systems with a lot at stake that need to perform well.Our approach represents a substantial improvement in malware detection, delivering a more efficient and versatile response to contemporary cyber threats.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| 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 | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".