User Modeling via Anomaly Detection Techniques for User Authentication
Bibliographic record
Abstract
Anomaly detection is quickly becoming a very significant tool for a variety of applications such as intrusion detection, fraud detection, fault detection, system health monitoring, and event detection in IoT devices. An application that lacks a strong implementation for anomaly detection is user trait modeling. User trait models expose up-to-date representation of the user so that changes in their interests, their learning progress or interactions with the system are noticed and interpreted. The reason behind the lack of adoption in user trait modeling arises from the need for a continuous flow of high-volume data, that is not available in most cases, to achieve high-accuracy detection. This paper provides new insight into the anomaly detection techniques through Big Data utilization. With Big Data characteristics, i.e., volume, variety and velocity, anomaly detection techniques have become more suitable tools for user trait modeling. User traits will be modeled by creating a security user profile for each user. This profile is structured and developed to be a source for a strong real-time user authentication method. An ingenious implementation of three models; k-means, HMM, and auto-encoder neural network has been presented that automatically and accurately build a unique pattern of the users' behavior. The implementation comprises four main steps: prediction of rare user actions, filter security potential actions, build/update a user profile, and generate a real-time (i.e. just in time) set of challenging questions. Real-world scenarios have been given showing the benefits of these challenging questions in building secure knowledge-based user authentication systems.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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 | 0.000 |
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 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".