ImmCOGNITO: Identity Obfuscation in Millimeter-Wave Radar-Based Gesture Recognition for IoT Environments

2026-02-06

AI Summary

This work addresses the privacy risk posed by identity leakage in millimeter-wave (mmWave) radar-based gesture recognition. To mitigate this issue, the authors propose a graph autoencoder approach that achieves identity de-identification on mmWave radar gesture data without requiring explicit identity labels. The method constructs directed graphs via temporal k-nearest neighbors and employs a multi-head self-attention message-passing network to aggregate spatiotemporal features. It jointly optimizes three objectives: point cloud reconstruction, preservation of gesture semantics, and suppression of identity-related features. Evaluated on the PantoRad and MHomeGes datasets, the approach significantly reduces identity recognition accuracy while maintaining high gesture recognition performance, effectively balancing privacy protection with task utility.

Technology Category

• Machine Learning: Privacy
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Biometrics, Face, Gesture & Pose

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Large-scale security measurements
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Millimeter-Wave (mmWave) radar enables camera-free gesture recognition for Internet of Things (IoT) interfaces, with robustness to lighting variations and partial occlusions. However, recent studies reveal that its data can inadvertently encode biometric signatures, raising critical privacy challenges for IoT applications. In particular, we demonstrate that mmWave radar point cloud data can leak identity-related information in the absence of explicit identity labels. To address this risk, we propose {ImmCOGNITO}, a graph-based autoencoder that transforms radar gesture point clouds to preserve gesture-relevant structure while suppressing identity cues. The encoder first constructs a directed graph for each sequence using Temporal Graph KNN. Edges are defined to capture inter-frame temporal dynamics. A message-passing neural network with multi-head self-attention then aggregates local and global spatio-temporal context, and the global max-pooled feature is concatenated with the original features. The decoder then reconstructs a minimally perturbed point cloud that retains gesture discriminative attributes while achieving de-identification. Training jointly optimizes reconstruction, gesture-preservation, and de-identification objectives. Evaluations on two public datasets, PantoRad and MHomeGes, show that ImmCOGNITO substantially reduces identification accuracy while maintaining high gesture recognition performance.

Problem

• mmWave radar
• gesture recognition
• identity obfuscation
• privacy
• biometric leakage

Innovation

• mmWave radar
• identity obfuscation
• graph autoencoder
• temporal graph
• privacy-preserving gesture recognition