Advances in Secure and Privacy-Preserving Machine Learning

The field of machine learning is shifting towards more secure and privacy-preserving approaches, with a focus on protecting sensitive data and preventing intellectual property theft. Researchers are exploring new paradigms, such as zero-trust foundation models and blockchain-powered edge intelligence, to enable secure and collaborative artificial intelligence.

Noteworthy papers in this area include:

Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things, which proposes a novel paradigm for secure and collaborative AI.
MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models, which introduces a novel defense strategy against model extraction attacks.
Federated Isolation Forest for Efficient Anomaly Detection on Edge IoT Systems, which presents an efficient federated anomaly detection algorithm for edge IoT systems.

Sources

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning

Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things

Searching Neural Architectures for Sensor Nodes on IoT Gateways

Adaptive Privacy-Preserving SSD

Smartphone-Based Food Traceability System Using NoSQL Database

Blockchain Powered Edge Intelligence for U-Healthcare in Privacy Critical and Time Sensitive Environment

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Decentralized COVID-19 Health System Leveraging Blockchain

Fingerprinting Deep Learning Models via Network Traffic Patterns in Federated Learning

Evaluating the Impact of Privacy-Preserving Federated Learning on CAN Intrusion Detection

Federated Isolation Forest for Efficient Anomaly Detection on Edge IoT Systems