Attack Assessment and Augmented Identity Recognition for Human Skeleton Data

• Published in: Proceedings of ... International Joint Conference on Neural Networks pp. 1 - 8
• Main Authors: Zalameda, Joseph G., Witherow, Megan A., Glandon, Alexander M., Aguilera, Jose, Iftekharuddin, Khan M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 18.06.2023
• Subjects: Data models; Generative adversarial networks; Human Identity Recognition; Laser radar; Model Robustness; Motion Capture Data; Perturbation methods; Robustness; Security; Skeleton; Skeleton Data; Small Data Set; Synthetic Data Generation; Training
• ISSN: 2161-4407
• DOI: 10.1109/IJCNN54540.2023.10191835

Machine learning models trained on small data sets for security applications are especially vulnerable to adversarial attacks. Person identification from LiDAR based skeleton data requires time consuming and expensive data acquisition for each subject identity. Recently, Assessment and Augmented Identity Recognition for Skeletons (AAIRS) has been used to train Hierarchical Co-occurrence Networks for Person Identification (HCN-ID) with small LiDAR based skeleton data sets. However, AAIRS does not evaluate robustness of HCN-ID to adversarial attacks or inoculate the model to defend against such attacks. Popular perturbation-based approaches to generating adversarial attacks are constrained to targeted perturbations added to real training samples, which is not ideal for inoculating models with small training sets. Thus, we propose Attack-AAIRS, a novel addition to the AAIRS framework. Attack-AAIRS leverages a small real data set and a generative adversarial network (GAN) generated synthetic data set to assess and improve model robustness against unseen adversarial attacks. Rather than being constrained to perturbations of limited real training samples, the GAN learns the distribution of adversarial attack samples that exploit weaknesses in HCN-ID. Attack samples drawn from this distribution augment training for inoculation of the HCN-ID to improve robustness. Ten-fold cross validation of Attack-AAIRS yields noticeable increase in robustness to unseen attacks-including Fast Gradient Sign Method, Projected Gradient Descent, Additive Gaussian Noise, Momentum Iterative Fast Gradient Sign Method, and Basic Iterative Method. The HCN-ID Synthetic Data Quality Score for Attack-AAIRS indicates that generated attack samples are of similar quality to the original benign synthetic samples generated by AAIRS. Furthermore, inoculated models show consistent final test accuracy with the original model trained on real data, demonstrating that our method improves robustness to adversarial attacks without reducing testing performance on real data.