mlsanityData to 14 Oct 2026

Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognition

arXiv 2411.02099 ↗First posted 4 Nov 2024cs.CV cs.AI cs.CRcited by 2

Not on the map. Why?

Abstract (arXiv)

Human motion analysis offers significant potential for healthcare monitoring and early detection of diseases. The advent of radar-based sensing systems has captured the spotlight for they are able to operate without physical contact and they can integrate with pre-existing Wi-Fi networks. They are also seen as less privacy-invasive compared to camera-based systems. However, recent research has shown high accuracy in recognizing subjects or gender from radar gait patterns, raising privacy concerns. This study addresses these issues by investigating privacy vulnerabilities in radar-based Human Activity Recognition (HAR) systems and proposing a novel method for privacy preservation using Differential Privacy (DP) driven by attributions derived with Integrated Decision Gradient (IDG) algorithm. We investigate Black-box Membership Inference Attack (MIA) Models in HAR settings across various levels of attacker-accessible information. We extensively evaluated the effectiveness of the proposed IDG-DP method by designing a CNN-based HAR model and rigorously assessing its resilience against MIAs. Experimental results demonstrate the potential of IDG-DP in mitigating privacy attacks while maintaining utility across all settings, particularly excelling against label-only and shadow model black-box MIA attacks. This work represents a crucial step towards balancing the need for effective radar-based HAR with robust privacy protection in healthcare environments.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 31 of its 89 references that are in the map. First posted on arXiv 4 Nov 2024.

Builds on

31 of 89 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  6. 2021Membership Inference Attacks From First Principlescited by 878
  7. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  8. 2020Label-Only Membership Inference Attackscited by 388
  9. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 348
  10. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  11. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
  12. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 197
19 more
  1. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  2. 2019DeepPrivacy: A Generative Adversarial Network for Face Anonymizationcited by 108
  3. 2020Privacy in Deep Learning: A Surveycited by 71
  4. 2022DeepPrivacy2: Towards Realistic Full-Body Anonymizationcited by 51
  5. 2022SPAct: Self-supervised Privacy Preservation for Action Recognitioncited by 47
  6. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  7. 2020Local Differential Privacy and Its Applications: A Comprehensive Surveycited by 41
  8. 2019Cross-Subject Transfer Learning in Human Activity Recognition Systems using Generative Adversarial Networkscited by 35
  9. 2020Against Membership Inference Attack: Pruning is All You Needcited by 32
  10. 2020Investigating Membership Inference Attacks under Data Dependenciescited by 32
  11. 2023STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognitioncited by 29
  12. 2020On the Effectiveness of Regularization Against Membership Inference Attackscited by 24
  13. 2017Privacy Risk in Machine Learning: Analyzing the Connection to Overfittingcited by 13
  14. 2020InfoScrub: Towards Attribute Privacy by Targeted Obfuscationcited by 10
  15. 2023Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decisioncited by 9
  16. 2021The Laplace Mechanism has optimal utility for differential privacy over continuous queriescited by 6
  17. 2024Privacy-preserving Optics for Enhancing Protection in Face De-identificationcited by 4
  18. 2021A Survey of Wearable Devices Pairing Based on Biometric Signalscited by 3
  19. 2022Privacy-Preserving Deep Learning Model for Covid-19 Disease Detectioncited by 3

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Differentially Private 2D Human Pose Estimationcited by 1
  2. 2025GraMFedDHAR: Graph Based Multimodal Differentially Private Federated HARcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Differentially Private Feature Release for Wireless Sensing: Adaptive Privacy Budget Allocation on CSI Spectrograms ↗
  2. 2024Approaches to human activity recognition via passive radar
  3. 2024Private Data Leakage in Federated Human Activity Recognition for Wearable Healthcare Devices ↗
  4. 2026OrganicHAR: Towards Activity Discovery in Organic Settings for Privacy Preserving Sensors Using Efficient Video Analysis
  5. 2025Neural-HAR: A Dimension-Gated CNN Accelerator for Real-Time Radar Human Activity Recognition
  6. 2024Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy
  7. 2026CLIP-guided Diffusion Model for Backdoor Generation in Sensor-based Human Activity Recognition
  8. 2025PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy