User and Event Behavior Analytics on Differentially Private Data for Anomaly Detection
Bibliographic record
Abstract
In today's world of digitization, anomaly detection has become one of the most important issues in our lives. User and Entity Behavior Analytics (UEBA) is a security solution for anomaly detection. UEBA minimizes the impact of attacks on data and decreases the risk of privacy breeches by keeping track of normal user and entity behaviors. Organizations need to deploy security control through UEBA in order to achieve security for their data by detecting attacks in their early stages, but the cost of such security control is often out of reach for many small and medium enterprises. One possible solution for such organizations is to outsource UEBA to third parties. However, such an approach can result in disclosure of private data. In this paper, we propose a novel scheme that integrates differential privacy into UEBA. We will show that by introducing noise to the data before publishing it to the third party for anomaly detection, we can ensure that the privacy of the data remains intact, while allowing the third party to preform accurate UEBA analysis. Our experimental results and security analysis will show the validity of our approach.
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 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.006 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".