A Hidden Markov Model security scheme for query state inference in discovery services
Bibliographic record
Abstract
Discovery Services refer to a suite of network services enabling efficient track-and-trace capabilities of objects in the Internet of Things (IoT). Deployment of such services may be performed in the form of simple queries originating from the corresponding stakeholders either to store/retrieve data in/from the Cloud. An example of such services is the EPCglobal Discovery Services. The extremely sensitive nature and the expected large scale of the exchanged data in the IoT (e.g, the EPCglobal Network) highlight the importance of a security scheme capable of distinguishing safe queries from risky ones, based both on a vector of observed real values extracted from the current query, and on a pattern inferred from the past queries. In this paper, we propose a probabilistic security scheme enhancing the accuracy of detecting risky queries in the EPCglobal Network. Our proposed scheme is based on a Hidden Markov Model (HMM) which is first trained, then used to infer the state of the query at hand. We assume that the observed real values, extracted from the queries, follow Gaussian distributions, depending on the inherent nature of the query at hand; i.e. safe or risky. We conducted extensive experiments. The results show that our HMM-based security scheme enhances the accuracy of detecting risky queries.
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 | 0.006 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 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".