A misbehavior detection framework for cooperative intelligent transport systems

Detecting contradictions from IoT protocol specification documents based on neural generated knowledge graph

Due to the boom of Internet of Things (IoT) in recent years, various IoT devices are connected to the Internet and communicate with each other through network protocols such as the Constrained Application Protocol (CoAP). These protocols are typically defined and described in specification documents, such as Request for Comments (RFC), which are written in natural or semi-formal languages. Since developers largely follow the specification documents when implementing web protocols, they have become the de facto protocol specifications. Therefore, it must be ensured that the descriptions in them are consistent to avoid technological issues, incompatibility, security risks, or even legal concerns. In this work, we propose Neural RFC Knowledge Graph (NRFCKG), a neural network-generated knowledge graph based contradictions detection tool for IoT protocol specification documents. Our approach can automatically parse the specification documents and construct knowledge graphs from them through entity extraction, relation extraction, and rule extraction with large language models. It then conducts an intra-entity and inter-entity contradiction detection over the generated knowledge graph. We implement NRFCKG and apply it to the most extensively used messaging protocols in IoT, including the main RFC (RFC7252) of CoAP, the specification document of MQTT, and the specification document of AMQP. Our evaluation shows that NRFCKG generalizes well to other specification documents and it manages to detect contradictions from these IoT protocol specification documents.

Backdoor attacks against distributed swarm learning

Traditional machine learning approaches often need a central server, where raw datasets or model updates are trained or aggregated in a centralized way. However, these approaches are vulnerable to many attacks, especially by the malicious server. Recently, a new distributed machine learning paradigm, called Swarm Learning (SL), has been proposed to support no-central-server based decentralized training. In each training round, each participant node has a chance to be selected to serve as a temporary server. Thus, these participant nodes do not need to share their private datasets to ensure a fair and secure model aggregation in a central server. To the best of our knowledge, there are no existing solutions about the security threats in swarm learning. In this paper, we investigate how to implant backdoor attacks against swarm learning to illustrate its potential security risk. Experiment results confirm the effectiveness of our method with high attack accuracies in different scenarios. We also study several defense methods to alleviate these backdoor attacks.

Privacy preserving federated learning for full heterogeneity

Federated learning is a novel distribute machine learning paradigm to support cooperative model training among multiple participant clients, where each client keeps its private data locally to protect its data privacy. However, in practical application domains, Federated learning still meets several heterogeneous challenges such data heterogeneity, model heterogeneity, and computation heterogeneity, significantly decreasing its global model performance. To the best of our knowledge, existing solutions only focus on one or two challenges in their heterogeneous settings. In this paper, to address the above challenges simultaneously, we present a novel solution called Full Heterogeneous Federated Learning (FHFL). Firstly, we propose a synthetic data generation approach to mitigate the Non-IID data heterogeneity problem. Secondly, we use knowledge distillation to learn from heterogeneous models of participant clients for model aggregation in the central server. Finally, we produce an opportunistic computation schedule strategy to exploit the idle computation resources for fast-computing clients. Experiment results on different datasets show that our FHFL method can achieve an excellent model training performance. We believe it will serve as a pioneer work for distributed model training among heterogeneous clients in Federated learning.