Hybrid Deep Learning Framework via Early Feature Fusion for XSS Attacks Detection
Bibliographic record
Abstract
Cross-site scripting (XSS) is still a significant security risk for online applications because it frequently avoids detection by using inventive payload formats and obfuscation.Most earlier studies either process statistical or sequential data alone or combine them at a later stage, which makes it difficult to capture their complementary interactions.This work differs from earlier approaches by integrating statistical and sequential representations at input stage, allowing both feature types to be learned jointly rather than fused later.Aiming to overcome this gap, this study suggests a hybrid deep learning framework that combines statistical features based on Term Frequency-Inverse Document Frequency (TF-IDF) with sequential dependencies learned through Long Short-Term Memory (LSTM) or Gated Recurrent Unit (GRU) networks using Early Feature Fusion.Principal Component Analysis (PCA) is used to reduce dimensionality in the TF-IDF dimension to enhance generalization.The proposed models have been evaluated on two well-known XSS datasets depending on eight key parameters.Both datasets, GRU and TF-IDF, performed well, with accuracy and F1-score exceeding 99%.The results indicate that early statistical and sequential feature fusion enhances the model's effectiveness in detecting malicious XSS payloads across the evaluated datasets.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| 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".