The field of edge computing is moving towards developing innovative solutions for secure and efficient data processing. Researchers are exploring new approaches to compress and augment data, enabling accurate classification and detection of anomalies in real-time. The use of machine learning models, such as variational autoencoders and XgBoost, is becoming increasingly popular for tasks like interference classification and cyberattack detection. Additionally, there is a growing interest in developing secure estimation methods for critical applications like battery management systems.

Noteworthy papers include: VAE-based Feature Disentanglement for Data Augmentation and Compression, which proposes a novel approach for compressing and augmenting data using variational autoencoders. Secure Estimation of Battery Voltage Under Sensor Attacks, which investigates a Koopman-based secure terminal voltage estimation scheme to ensure accurate terminal voltage data under malicious sensor attacks. Transfer Learning Assisted XgBoost For Adaptable Cyberattack Detection, which proposes an adaptable fine-tuning of an XgBoost-based cell-level model for detecting sensor cyberattacks in real-time. Reconstructing Fine-Grained Network Data using Autoencoder Architectures with Domain Knowledge Penalties, which proposes a machine learning approach guided by formal methods to encode and reconstruct network data. Enhanced Battery Capacity Estimation in Data-Limited Scenarios through Swarm Learning, which proposes a swarm battery management system that unites a decentralized swarm learning framework and credibility weight-based model merging mechanism to enhance battery capacity estimation.