FreqLT: Frequency-Domain Linear Transformation for Privacy-Preserving and Efficient Machine Learning on Wearable Sensor Signals
Bibliographic record
Abstract
The proliferation of wearable computing devices has enabled unprecedented opportunities for personalized health monitoring and human-computer interaction. However, the continuous stream of highly sensitive physiological and kinematic data they generate poses significant privacy and security risks, especially when processed on untrusted cloud-based Machine Learning as a Service (MLaaS) platforms. Existing privacy-preserving techniques present a stark tradeoff: cryptographic methods like Homomorphic Encryption offer robust security but are computationally prohibitive for resource-constrained wearables, while simpler perturbation-based methods degrade model performance and offer weak privacy guarantees. To address this challenge, we propose FreqLT, a novel and lightweight framework for Privacy-Preserving and Efficient Machine Learning on wearable devices. The core insight of FreqLT is that the discriminative information for most sensor-based ML tasks resides in the frequency domain. It is a learnable, invertible linear transformation directly to the frequency-domain representation of the sensor data, effectively obscuring the original signal's time-domain characteristics and sensitive statistical properties. Our experiments on different datasets show that FreqLT provides superior privacy protection compared to other methods.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".