ActivityNet-HE: An Encryption-Enabled Deep Learning-Based Framework for Secure Human Activity Monitoring
Bibliographic record
Abstract
An increasingly popular non-intrusive monitoring technique in smart environments is the recognition of human activities using Wi-Fi Channel State Information (CSI). However, the exposure of raw CSI data during processing poses significant privacy risks. This paper presents ActivityNet-HE, a deep learning framework designed to perform secure activity recognition through homomorphic encryption. The framework utilizes Principal Component Analysis (PCA) to minimize the dimensionality of the data makes it efficient to compute and extracts 29 statistical and signal-based features from time and frequency domains for each PCA stream. A lightweight neural network with polynomial activation enables encrypted inference without revealing sensitive input data. Evaluated on the CSI-HAR dataset, the model achieves 94.05% accuracy on both encrypted and plain data, demonstrating that strong privacy preservation can be achieved without sacrificing performance. While the system ensures secure inference, it incurs additional latency due to encryption overhead, which may limit its use in low-latency real-time applications. This makes the framework especially relevant for privacy-sensitive cases like monitoring the stereotypical motor movement (SMM) of autistic children in home or healthcare settings.
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 | 0.001 | 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 | 0.001 | 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".