Meta Learning for Enhanced Web Security Against Malicious URLs
Bibliographic record
Abstract
Abstract The identification of malicious Uniform Resource Locators (URLs) plays a pivotal role in strengthening network and cyber security. Over the years, the Internet has increasingly become a breeding ground for a multitude of cybercrimes. Malicious URLs can disrupt network performance, compromise data integrity, and introduce vulnerabilities into the system, impacting the network's overall security and reliability. Taking precautions and implementing preventative techniques is crucial for shielding users from cyberattacks. This study utilizes meta-learning, which is a machine learning technique that learns from the predictions of other machine learning algorithms to make better decisions. For a comprehensive evaluation, the ISCX-URL-2016 dataset was utilized, a resource curated by the Canadian Institute for Cyber Security. The proposed approach focuses on utilizing URL strings as the primary source of information for detecting malicious content.The performance of different machine learning algorithms, including Histogram-based Gradient Boosting Classification Tree, XGBoost Classifier, CatBoost Classifier, Random Forest Classifier and more, were compared for the detection of malicious URLs. The two best performing base classifiers were identified and evaluated as potential meta-classifiers. Various combinations of base classifiers were then tested in conjunction with these two selected meta-classifiers. A significant improvement in the accuracy was observed and the best accuracy of 98.25% was achieved using All Base Classifiers + Meta Classifier XGBoost. Closely followed by the Three Best Base Classifiers + Meta Classifier XGBoost, which achieved an accuracy of 98.2%.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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 | 0.001 |
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 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".