Securing Contrastive mmWave-based Human Activity Recognition against Adversarial Label Flipping

2026-08-01

AI Summary

This study addresses the vulnerability of millimeter-wave-based supervised contrastive learning systems for human activity recognition (HAR) to label-flipping poisoning attacks, systematically revealing for the first time their susceptibility within the contrastive learning framework. To counter this threat, the work proposes three novel label-flipping attack strategies alongside corresponding robust defense mechanisms that integrate adversarial example generation with robust training protocols, thereby significantly enhancing model stability under label corruption. Experimental validation on a prototype system demonstrates that the proposed attack and defense methods not only substantially improve robustness in millimeter-wave HAR scenarios but also exhibit strong generalizability to other wireless HAR systems.

Abstract

Wireless Human Activity Recognition (HAR), leveraging their non-intrusive nature, has the potential to revolutionize various sectors, including healthcare, virtual reality, and surveillance. The advent of millimeter wave (mmWave) technology has significantly enhanced the capabilities of wireless HAR systems. This paper presents the first systematic study on the vulnerabilities of mmWave-based HAR to label flipping poisoning attacks in the context of supervised contrastive learning. We identify three label poisoning attacks on the contrastive mmWave-based HAR and propose corresponding countermeasures. The efficacy of the attacks and also our countermeasures are experimentally validated on a prototype system. The attacks and countermeasures can be easily extended to other wireless HAR systems, thereby promoting security considerations in system design and deployment.

Problem

• mmWave
• Human Activity Recognition
• Label Flipping
• Adversarial Attack
• Contrastive Learning

Innovation

• mmWave-based HAR
• label flipping attack
• contrastive learning
• adversarial poisoning
• security countermeasures