Análisis y detección de Tráfico Malicioso mediante Machine Learning y Deep Learning
Bibliographic record
Abstract
Los ataques distribuidos de denegación de servicio (DDoS) aparecieron por primera vez a mediados de los años 90, como ataques que impedían a los usuarios legítimos acceder a determinados servicios disponibles en Internet. Un ataque DDoS intenta agotar los recursos de la víctima para colapsar o suspender sus servicios. El Trabajo de Fin de Grado se centra en la aplicación de técnicas de inteligencia artificial al dataset CICDDoS2019 del Instituto Canadiense de Ciberseguridad, con el objetivo de diferenciar entre tráfico de red legítimo y tráfico de red malicioso. Se implementan y evalúan varios modelos de aprendizaje automático y aprendizaje profundo para identificar patrones de tráfico malicioso y detectar ataques DDos. El proyecto incluye una fase de preprocesamiento de datos, selección de características relevantes, y ajuste de modelos. Los resultados son analizados para determinar la efectividad de cada modelo en la clasificación precisa del tráfico, contribuyendo así a mejorar las estrategias de ciberseguridad. Abstract: Distributed Denial of Service (DDoS) attacks first appeared in the mid-1990s as attacks that prevented legitimate users from accessing certain services available on the Internet. A DDoS attack attempts to exhaust the victim's resources to crash or suspend its services. The Final Degree Work focuses on the application of artificial intelligence techniques to the Canadian Cybersecurity Institute's CICDDoS2019 dataset, with the objective of differentiating between legitimate network traffic and malicious network traffic. Several machine learning and deep learning models are implemented and evaluated to identify malicious traffic patterns and detect DDoS attacks. The project includes a data preprocessing phase, selection of relevant features, and model fitting. The results are analyzed to determine the effectiveness of each model in accurately classifying traffic, thus contributing to improve cybersecurity strategies.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".