Leveraging Dual-Generative Adversarial Networks for Adversarial Malware Detection via Ensemble Learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract

 
 
 
 In the expanding realm of cybersecurity, machine learning-based malware detection has emerged as a vital line of defense. However, the growing sophistication of malware attacks poses formidable challenges to conventional detection systems. To address this, this paper uses a Generative Adversarial Network that utilizes dual generators for adversarial learning on malware, designed to enhance the detection of harmful Portable Executable (PE) files. Our model employs a two-tiered generator system within the GAN architecture, where the secondary generator intervenes when the primary generator yields a malware PE executable dismissed by the detector.
 The detection unit leverages ensemble learning techniques to analyze the PE software feature vector, capitalizing on the synergy of multiple learning models for improved performance and generalization. This setup empowers the system to generate a broader range of adversarial examples and respond to them effectively, enhancing the robustness of the detector against previously unseen or variable malware types.
 
 
 
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.
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 | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| 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 it