Self-organizing feature maps for User-to-Root and Remote-to-Local network intrusion detection on the KDD Cup 1999 dataset
Bibliographic record
Abstract
The problem of network intrusion detection is one that is ever-changing, ever-evolving, and is always in need of improvement. Society-at-large relies on computer networks everyday for tasks ranging from online banking to e-commerce, social networking, news, gambling, and just about anything else. As such, society demands that these networks remain secure. In order to maintain security the systems used to protect these networks, which are vital to the 21st century world, must be constantly updated. The task of creating a system for the 21st century fell upon several groups for the ACM 1999 KDD Cup Competition. The competition produced a winning entry, but something was lacking: The winning team's results for two of the intrusion types, User-to-Root and Remote-to-Local, were subpar at best. The winning team produced a 13.8% and 8.4% detection rate for these types respectively, compared to over 90% for each of the Denial of Service and Probing intrusion types. This research aimed to rectify this shortcoming. By implementing an unsupervised learning system, this research has produced a system that correctly detects 62.8% of User-to-Root attacks within the same dataset, with minimal false positives, while maintaining the high detection rates of Denial of Service and Probing attacks.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.003 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.008 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.002 |
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".