Adversary-Aware Private Inference over Wireless Channels

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seif, Mohamed, Egan, Malcolm, Goldsmith, Andrea J., Poor, H. Vincent
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908792931745792
author Seif, Mohamed
Egan, Malcolm
Goldsmith, Andrea J.
Poor, H. Vincent
author_facet Seif, Mohamed
Egan, Malcolm
Goldsmith, Andrea J.
Poor, H. Vincent
contents AI-based sensing at wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for vision and perception tasks such as in autonomous driving and environmental monitoring. AI systems rely both on efficient model learning and inference. In the inference phase, features extracted from sensing data are utilized for prediction tasks (e.g., classification or regression). In edge networks, sensors and model servers are often not co-located, which requires communication of features. As sensitive personal data can be reconstructed by an adversary, transformation of the features are required to reduce the risk of privacy violations. While differential privacy mechanisms provide a means of protecting finite datasets, protection of individual features has not been addressed. In this paper, we propose a novel framework for privacy-preserving AI-based sensing, where devices apply transformations of extracted features before transmission to a model server.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20518
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adversary-Aware Private Inference over Wireless Channels
Seif, Mohamed
Egan, Malcolm
Goldsmith, Andrea J.
Poor, H. Vincent
Information Theory
Cryptography and Security
Machine Learning
AI-based sensing at wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for vision and perception tasks such as in autonomous driving and environmental monitoring. AI systems rely both on efficient model learning and inference. In the inference phase, features extracted from sensing data are utilized for prediction tasks (e.g., classification or regression). In edge networks, sensors and model servers are often not co-located, which requires communication of features. As sensitive personal data can be reconstructed by an adversary, transformation of the features are required to reduce the risk of privacy violations. While differential privacy mechanisms provide a means of protecting finite datasets, protection of individual features has not been addressed. In this paper, we propose a novel framework for privacy-preserving AI-based sensing, where devices apply transformations of extracted features before transmission to a model server.
title Adversary-Aware Private Inference over Wireless Channels
topic Information Theory
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2510.20518