An Anomalous Behavior Detection Method for Complex Networks Based on Image Processing and Protocol Evolution Modeling
Bibliographic record
Abstract
With the rapid development of information technology, complex networks are increasingly vulnerable to abnormal behaviors such as malicious attacks and data breaches due to their growing scale and structural complexity.Traditional detection methods often struggle in dynamic network environments due to insufficient utilization of temporal features and lack of protocol evolution analysis, resulting in suboptimal detection accuracy.Existing studies based on conventional machine learning typically ignore the temporal characteristics of network behaviors and the evolutionary nature of protocols.Similarly, image processing techniques alone fail to incorporate protocol-level information, while static protocol models cannot adapt to dynamically changing scenarios, leading to incomplete extraction of essential features of anomalous behaviors.To address these challenges, this paper proposes a novel detection method that integrates image processing with protocol evolution modeling.The main contributions are as follows: (1) A method for visual mapping of temporal network behaviors is designed, converting dynamic behaviors into interpretable image features; (2) A protocol evolution prediction model is constructed, combining time series analysis with machine learning techniques to capture the dynamics of protocol changes; (3) A multimodal behavior recognition model is developed, integrating image features with protocol evolution features to accurately detect anomalous behaviors.By leveraging cross-disciplinary techniques, this study overcomes the limitations of existing approaches in temporal feature utilization, dynamic protocol modeling, and multimodal data fusion.It offers a novel framework that supports both visual analysis and dynamic mechanism modeling, contributing to improved accuracy and robustness in detecting anomalous behaviors in complex networks.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".