A Multilabel Fuzzy Relevance Clustering System for Malware Attack Attribution in the Edge Layer of Cyber-Physical Networks
Bibliographic record
Abstract
The rapid increase in the number of malicious programs has made malware forensics a daunting task and caused users’ systems to become in danger. Timely identification of malware characteristics including its origin and the malware sample family would significantly limit the potential damage of malware. This is a more profound risk in Cyber-Physical Systems (CPSs), where a malware attack may cause significant physical damage to the infrastructure. Due to limited on-device available memory and processing power in CPS devices, most of the efforts for protecting CPS networks are focused on the edge layer, where the majority of security mechanisms are deployed. Since the majority of advanced and sophisticated malware programs are combining features from different families, these malicious programs are not similar enough to any existing malware family and easily evade binary classifier detection. Therefore, in this article, we propose a novel multilabel fuzzy clustering system for malware attack attribution. Our system is deployed on the edge layer to provide insight into applicable malware threats to the CPS network. We leverage static analysis by utilizing Opcode frequencies as the feature space to classify malware families. We observed that a multilabel classifier does not classify a part of samples. We named this problem the instance coverage problem. To overcome this problem, we developed an ensemble-based multilabel fuzzy classification method to suggest the relevance of a malware instance to the stricken families. This classifier identified samples of VirusShare, RansomwareTracker, and BIG2015 with an accuracy of 94.66%, 94.26%, and 97.56%, respectively.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".