Skip to content
AI Atlas
PaperActive

mmFHE: mmWave Sensing with End-to-End Fully Homomorphic Encryption

arxiv.org/abs/2603.22437

Updated 53 min ago · first seen 11 Sept 2026

paper_01M294FT37GX4ZMKH45SW5Q5XJ

Published
11 Sept 2026
T1 · 53 min ago
arXiv
2603.22437
T1 · 53 min ago
Category
cs.CR
T1 · 53 min ago

Abstract

-cross Abstract: We present mmFHE, the first system that executes the entire cloud-side mmWave sensing pipeline including the DSP and ML inference under fully homomorphic encryption (FHE). mmFHE encrypts range profiles on an edge device after lightweight plaintext preprocessing and executes the entire mmWave signal-processing and ML inference pipeline homomorphically on a semi-honest cloud that operates exclusively on ciphertexts. At the core of mmFHE is a library of seven composable, data-oblivious FHE kernels that replace standard DSP routines with fixed arithmetic circuits for different application-specific pipelines. We demonstrate this approach on two representative tasks: vital-sign monitoring and gesture recognition. We formally prove two cryptographic guarantees for any pipeline assembled from this library: input privacy and data obliviousness. These guarantees effectively neutralize various supervised and unsupervised privacy attacks on raw data, including re-identification and data-dependent privacy leakage. Evaluation on three public radar datasets shows that encryption introduces negligible error versus the plaintext pipeline, with 84.5% gesture accuracy (vs. 84.7%). End-to-end cloud GPU latency is 1.21 s per 10 s vital-sign window and 5.76 s per 3 s gesture window. These results establish the initial feasibility of end-to-end mmWave sensing under FHE on commodity hardware.

Authors 4

Tanvir Ahmed, Yixuan Gao, Adnan Armouti, Rajalakshmi Nandakumar

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 53 min agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 53 min agohigh

arXiv id
2603.22437

Source:arXiv (Atom API + RSS)T1observed 53 min agohigh

Categories
cs.CR, cs.LG, eess.SP

Source:arXiv (Atom API + RSS)T1observed 53 min agohigh

DOI
10.1145/3795866.3844486

Source:arXiv (Atom API + RSS)T1observed 53 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 53 min agohigh

Primary category
cs.CR

Source:arXiv (Atom API + RSS)T1observed 53 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 53 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

10

Source tiers

T110

Freshest observation

53 min ago

Conflicts

None