ReBotDetector: A Detection Model with LSTM Feature Extractor for Session-Replay Web Bot Attacks
Bibliographic record
Abstract
In the ever-evolving digital landscape, cyberattacks are becoming increasingly intricate and adept at bypassing detection. Session-replay web bot attacks, where attackers leverage pre-recorded human mouse movements to mimic user behavior on targeted websites and applications, exemplify this growing threat. This paper proposes ReBotDetector, a specialized ML-based system designed to identify malicious replay sessions. In the first stage of its operation, ReBotDetector utilizes a Long Short-Term Memory (LSTM) network to extract the most critical features from human-generated dynamic mouse-movement dataset. Subsequently, it employs Cosine similarity to pinpoint sessions exhibiting a high degree of similarity with previously observed legitimate human sessions. The effectiveness of ReBotDetector is evaluated through experiments utilizing our proprietary state-of-the-art replay bot software (ReBot), which is designed to faithfully replicate authentic human sessions. Experimental results demonstrate that ReBotDetector is highly effective at identifying malicious replay sessions generated by ReBot against genuine human sessions. The high accuracy achieved in detecting these replay sessions underscores our proposed model's potential as a robust defense against session-replay bot attacks in real-world 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 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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".