In machine learning (ML), near-sensor AI is transforming edge computing by reducing response times and data transmission, ultimately saving energy and bandwidth. Despite challenges like limited computational resources and the need for transparent decision-making, this approach aims to enhance the intelligence and autonomy of edge devices. Our research presents a novel framework that adds a layer of abstract intelligence to sensors, boosting system efficiency and accuracy through transparent, interpretable sub-symbolic AI. We combine Bayesian algorithms with hyperdimensional computing (HDC), inspired by the human brain's operational efficiency, to deliver an energy-efficient solution matching the accuracy of traditional cloud systems without constant server dependence. This framework uses a binary classifier with Bayesian insights to choose the best data processing location---locally or in the cloud---adapting to data environments. Our method ensures cloud-level performance while significantly reducing energy consumption, improving the sustainability of sensor-based systems. It also enables continual adaptation and learning directly at the sensor level, enriching cloud models with fresh edge insights. Our results have shown to bridge the gap from around 38% quality loss between the standalone near-sensor HDC model and the SOTA cloud-based model to improve the quality loss to only 9% while simultaneously saving 45.34% of energy by not using the cloud. This framework paves the way for more sustainable, efficient, and accurate edge computing in the ML landscape by bridging the gap between simple near-sensor models and their advanced cloud-based counterparts.

Brain-inspired Hyper-dimensional computing (HDC) has recently shown promise as a lightweight machine learning approach. Despite its success, there are limited studies on the robustness of HDC models to adversarial attacks. In this paper, we introduce the first comparative study of the robustness between HDC and deep neural network (DNN) to malicious attacks. We develop a framework that enables HDC models to generate gradient-based adversarial examples using state-of-the-art techniques applied to DNNs. Our evaluation shows that HDC with a proper neural encoding module provides significantly higher robustness to adversarial attacks than existing DNNs. In addition, HDC models have high robustness to adversarial samples generated for DNNs.

Recent strides in deep learning have yielded impres-sive practical applications such as autonomous driving, natural language processing, and graph reasoning. However, the sus-ceptibility of deep learning models to subtle input variations, which stems from device imperfections and non-idealities, or adversarial attacks on edge devices, presents a critical challenge. These vulnerabilities hold dual significance-security concerns in critical applications and insights into human-machine sen-sory alignment. Efforts to enhance model robustness encounter resource constraints in the edge and the black box nature of neural networks, hindering their deployment on edge devices. This paper focuses on algorithmic adaptations inspired by the human brain to address these challenges. Hyper Dimensional Computing (HDC), rooted in neural principles, replicates brain functions while enabling efficient, noise-tolerant computation. HDC leverages high-dimensional vectors to encode information, seamlessly blending learning and memory functions. Its trans-parency empowers practitioners, enhancing both robustness and understanding of deployed models. In this paper, we introduce the first comprehensive study that compares the robustness of HDC to white-box malicious attacks to that of deep neural network (DNN) models and the first HDC gradient-based attack in the literature. We develop a framework that enables HDC models to generate gradient-based adversarial examples using state-of-the-art techniques applied to DNNs. Our evaluation shows that our HDC model provides, on average, 19.9% higher robustness than DNNs to adversarial samples and up to 90% robustness improvement against random noise on the weights of the model compared to the DNN.