Detection of False Data Injection Attacks in Industrial Wireless Sensor Networks Exploiting Network Numerical Sparsity
Bibliographic record
Abstract
Existing studies on false data injection attacks, a type of stealth attacks against sensor networks aimed at compromising the system in the cyber-physical security domain, have primarily been conducted on wired systems for applications such as advanced metering infrastructure in smart grid. However, the emerging trend of the widespread deployment of industrial wireless sensor networks for various new functionalities as well as for replacement of legacy systems, on the other hand, calls for both data aggregation methods that are cost-effective, scalable and easily implementable, as well as feasible approaches to detect injected false data in coordination with such data aggregation models. In this paper, we propose a numerical sparsity-based detection scheme operating upon a network coding-based data aggregation model paired with compressed sensing-based decoding, against attacks that alter the overall network sparsity by compromising and injecting falsified data into multiple sensor nodes in the network. Both the applicative scope and performance of the proposed scheme are analyzed and compared to a more straightforward but realistically challenging approach of directly examining network compressibility, i.e. the number of sufficiently large readings of active nodes extracted from the decoded network signal. Numerical studies illustrate the proposed method is applicable for the usually sparsely active industrial wireless sensor networks, and offers faster, reliable decisions when the aforementioned false data injection attacks are launched.
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 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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 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".