Practical and Secure SVM Classification for Cloud-Based Remote Clinical Decision Services
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Support vector machine (SVM) classification techniques have been widely adopted for building clinical decision models. In cloud-based remote clinical decision services, a healthcare center outsources the clinical decision model to a cloud server, which then provides remote clinical decision services to end users. In this article, we propose a practical and secure SVM classification scheme ( <inline-formula><tex-math notation="LaTeX">${\sf SSVMC}$</tex-math></inline-formula> ) for cloud-based remote clinical decision services. Specifically, we first extract SVM decision rules from an SVM classifier. Then, we leverage symmetric key encryption to protect the confidentiality of medical data and prevent the cloud service provider from misusing intellectual property of the outsourced clinical model. Finally, we build encrypted indexes to achieve efficient SVM classification. We define a leakage function, formulate a security definition, and provide a simulation-based security proof for <inline-formula><tex-math notation="LaTeX">${\sf SSVMC}$</tex-math></inline-formula> . The performance analysis demonstrates that <inline-formula><tex-math notation="LaTeX">${\sf SSVMC}$</tex-math></inline-formula> achieves linear computational complexity when an SVM classifier (a.k.a., the clinical decision model) is pre-trained. The simulations evaluate the impact of several parameters on time costs. The experimental evaluations show the performance differences between <inline-formula><tex-math notation="LaTeX">${\sf SSVMC}$</tex-math></inline-formula> and several existing schemes in terms of time costs, storage costs, communication costs, and precisions in a real-world clinical dataset, which demonstrate that <inline-formula><tex-math notation="LaTeX">${\sf SSVMC}$</tex-math></inline-formula> is computationally efficient with high decision accuracy.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.005 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it