THE PROBLEM OF ACCURACY IN SYSTEMS FOR CYBERATTACK RESISTANCE AND THE VERIFICATION OF NEURAL NETWORKS ON THE EXAMPLE OF BOTNET DETECTING PROBLEM
Bibliographic record
Abstract
The paper considers the problem of the accuracy of detection of intrusions in software systems based on deep learning neural networks. An example of a system for detecting botnets, malicious software, which are the source of potential attacks, including Denial of Service (DDoS), is presented. The system is created as a classification model that detects the behavior of botnets on infected resources. A number of experiments were conducted on the open data set of the Canadian Institute for Cybersecurity. To increase the accuracy of the classification, the method of augmentation of the data set using the method of generating examples of adversarial attacks was used. A method for verification of the reliability of a neural network using automatic proof of the robustness property of the model based on SMT solvers is presented. To increase the accuracy of attack detection, a neurosymbolic approach that combines algebraic methods with classification models is also considered. Keywords: cyber security, botnet, algebraic modelling, deep learning neural network, adversarial attacks, verification.
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 | 0.010 | 0.087 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.003 | 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".