With the rise of the smart industry, machine learning (ML) has become a popular method to improve the security of the Industrial Internet of Things (IIoT) by training anomaly detection models. Federated learning (FL) is a distributed ML scheme that facilitates anomaly detection on IIoT by preserving data privacy and breaking data silos. However, poisoning attacks pose significant threats to FL, where adversaries upload poisoned local models to the aggregation server, thereby degrading model accuracy. The prevalence of non-independent and identically distributed (non-IID) data across IIoT devices further exacerbates this threat, as it naturally leads to diverse local models, making malicious ones harder to distinguish. To address the above challenges, we propose a deep-layer sign-sharing personalized FL (DSPFL) scheme. DSPFL innovatively aggregates only the signs of stochastic gradients (SignSGD) from the deep layers of local models during training. This targeted aggregation enhances the robustness of the shared components against poisoning attacks, while shallow layers are retained locally to preserve personalization. This integrated approach improves the accuracy and resilience of personalized local models on IIoT devices under poisoning attacks. Extensive experimental results show that DSPFL consistently achieves up to 20% higher and more stable overall personalized model accuracy compared to state-of-the-art methods under specific poisoning attacks.

While the Vision Transformer (ViT) architecture gains prominence in computer vision and finds growing applications in edge computing, its lack of strong inductive biases regarding shift, scale, and rotational invariance necessitates pre-training on large-scale datasets. Moreover, the increasing depth and parameter counts in ViT models present significant challenges for training, particularly in edge environments where computational resources are constrained. To mitigate these challenges, this paper introduces a novel Horizontally Scalable Vision Transformer (HSViT) architecture. Specifically, a novel image-level feature embedding approach is introduced that incorporates convolutional layers prior to the Transformer blocks. This design helps preserve inductive biases, allowing the model to potentially eliminate the need for pre-training while achieving strong performance on small datasets. Furthermore, a novel horizontally scalable architecture is designed, facilitating collaborative model training and inference across multiple edge devices. The experimental results show that, without pre-training, HSViT achieves up to 10% higher top-1 accuracy than state-of-the-art methods on several small datasets, while improving the top-1 accuracy of existing CNN backbones by up to 3.1% on ImageNet-1k. The code is available at https://github.com/xuchenhao001/HSViT.

Deepfake detection is essential for mitigating the growing risks associated with the misuse of AI in video manipulation. While existing deep learning-based methods excel in intra-dataset settings, their performance often deteriorates significantly when applied to unseen datasets, underscoring the pressing challenge of improving generalization capability. To tackle this challenge, we focus on identitying discriminative regions by applying the principle of object detection, which locating forged clues. In this paper, we propose an aggregated distinguishable feature learning framework that innovatively incorporates object detector with a graph claasifier. Specifically, the proposed framework consists of three main components: 1) We employ a DEtection TRansformer (DETR) to learn intrinsic feature differences for capturing different discriminative regions. 2) To better utilize distinguishable features in these regions, we treat each local feature vector of the regions as node and design a node correlation generation module (NCGM) to establish the connections between the nodes by integrating the feature similarity and spatial location relationship. 3) we employ graph convolutional neural networks to aggregate the distinguishable features and learn the global connectivity pattern of the nodes for face forgery detection. Comprehensive experimental results on four benchmark datasets demonstrate that our method effectively improves generalization capability and outperforms other state-of-the-art approaches.

Video Instance Segmentation (VIS), also known as multi-object tracking and segmentation, represents a fundamental challenge in computer vision that requires simultaneous detection, segmentation, and tracking of object instances across video frames. This complex task has gained significant attention due to its crucial role in various real-world applications. The advent of deep learning has promoted VIS approaches, leading to numerous architectural innovations and performance improvements. This survey presents a systematic review of deep learning-based VIS methods, introducing a novel categorization based on temporal modeling strategies: frame-by-frame, clip-based, in-memory feature propagation, and in-memory object query propagation. Comprehensive quantitative comparisons of existing work across three major VIS benchmark datasets are also provided. Additionally, emerging challenges in the field are explored, with several promising research directions identified, aiming to provide valuable insights for researchers and practitioners interested in VIS, while further advancing deep learning techniques for VIS. • Categorization of VIS approaches based on their temporal modeling strategies. • Comprehensive quantitative comparison of current VIS methods. • Analysis of the challenges and potential future research directions in VIS.

The consortium blockchain is being utilized in supply chains on the Internet of Things (IoT) for tracking and protecting supply chain data, such as manufacture, storage, and shipment. However, the supply chain data in a consortium blockchain is publicly accessible for all parties, which attracts widespread concerns about supply chain data privacy. Several existing attribute-based encryption (ABE)-based blockchain systems targeting to address the supply chain data privacy problem either bring about additional security problems or lack the feasibility analysis on IoTs. To address the aforementioned issues, in this article, a novel multiauthority ABE (MA-ABE)-based blockchain system is proposed to protect the data privacy for the supply chain on IoTs. Specifically, a four-way tradeoff optimization framework is designed so that the system decentralization, scalability, and storage consumption are not significantly affected by the improved privacy. The optimal attribute setting policies for different scale blockchain networks are dynamically generated by the nondominated sorting genetic algorithm II (NSGA-II). Extensive experiment results show that the proposed scheme remarkably improves data privacy protection for the supply chain without downgrading the other three key factors.

Edge intelligence, an emerging distributed paradigm, is driven by the increasing number of Internet of Things devices and the development of edge computing and artificial intelligence. This paradigm revolutionizes the way of data caching by encouraging latency-sensitive data to be distributed across multiple edge nodes. In such data caching scenarios, ensuring the integrity of data stored at the edge nodes is critical for business continuity guarantee. Existing Edge Data Integrity (EDI) verification solutions rely on the interactive Challenge-Response mechanism. However, this mechanism imposes significant communication overhead on participants, leading to low verification efficiency. To address this challenge, we propose a Learning-based Hierarchical Edge Data Corruption Detection framework (LH-EDCD), aiming to enhance verification efficiency from a round perspective by reducing communication interaction between edge nodes and the data owner. LH-EDCD involves two layers of verification: internal and external. In the internal verification layer, each edge node self-inspects the cached data replica by running a corruption detection model distributedly trained by blockchain-based Federated Learning (FL). With such filtration, potential corruption can be efficiently identified without complex interaction. Considering the false positive existence in the model, in the external verification layer, LH-EDCD adopts a smart contract in blockchain to verify identified potentially corrupted data replicas for corruption confirmation, mitigating the trust concerns among edge nodes while reducing communication overhead on backbone networks. With the combination of these two layers, the overall EDI verification efficiency can be improved by reducing interaction verification time. Additionally, we make the first attempt to investigate the optimal verification time to improve the applicability and practicality of LH-EDCD. Extensive experimental results substantiate the advantages of employing FL in the first layer of LH-EDCD and demonstrate that LH-EDCD outperforms two state-of-the-art EDI approaches, i.e., EDI-S and EDI-V. Specifically, LH-EDCD achieves better model accuracy and convergence speed compared to centralized training, while exhibiting superior efficiency over EDI-S and EDI-V with 3.5 and 2.8 times performance improvements, respectively.

Federated learning (FL) is a distributed framework for machine learning that enables collaborative training of a shared model across data silos while preserving data privacy. However, the FL aggregation server faces a challenge in waiting for a large volume of model parameters from selected nodes before generating a global model, which leads to inefficient communication and aggregation. Although transmitting only the signs of stochastic gradient descent (SignSGD) reduces the transmission load, it decreases model accuracy, and the time waiting for local model collection remains substantial. Moreover, the security of FL is severely compromised by prevalent poisoning, backdoor, and DDoS attacks, causing ineffective and inaccurate model training. To overcome these challenges, this paper proposes aBlockchain-basedAsynchronousSignSGD (BASS) architecture for efficient and secure federated learning. By integrating a blockchain-based semi-asynchronous aggregation scheme with sign-based gradient compression, BASS considerably improves communication and aggregation efficiency, while providing resistance against attacks. Besides, a novel node-summarized sign aggregation algorithm is developed for the blockchain leaders to ensure the convergence and accuracy of the global model. An open-source prototype is developed, on top of which extensive experiments are conducted. The results validate the superiority of BASS in terms of efficiency, model accuracy, and security.

Federated learning (FL) enables collaborative training of a shared model on edge devices while maintaining data privacy. FL is effective when dealing with independent and identically distributed (iid) datasets, but struggles with non-iid datasets. Various personalized approaches have been proposed, but such approaches fail to handle underlying shifts in data distribution, such as data distribution skew commonly observed in real-world scenarios (e.g., driver behavior in smart transportation systems changing across time and location). Additionally, trust concerns among unacquainted devices and security concerns with the centralized aggregator pose additional challenges. To address these challenges, this paper presents a dynamically optimized personal deep learning scheme based on blockchain and federated learning. Specifically, the innovative smart contract implemented in the blockchain allows distributed edge devices to reach a consensus on the optimal weights of personalized models. Experimental evaluations using multiple models and real-world datasets demonstrate that the proposed scheme achieves higher accuracy and faster convergence compared to traditional federated and personalized learning approaches.

Federated learning (FL) is a machine learning framework for collaborative data mining in many scenarios (e.g. Internet of Things) due to its privacy-preserving feature. However, various attacks arise security concerns of FL, such as poisoning, backdoor, and DDoS attacks. Several blockchain-based FL schemes strengthen credibility and security without considering the increased communication overhead. Some existing work compresses local updated gradients to sign vectors to lower communication overhead at the expense of model accuracy. To address the above concerns, this paper offers a blockchain-based asynchronous SignSGD (BASS) scheme. A novel asynchronous sign aggregation algorithm is introduced to ensure model accuracy even if the local updated gradients are compressed to sign vectors. Considering the unstable network connection on IoT, a consensus algorithm that elects multiple leader nodes enables reliable global model aggregation. The introduced blockchain improves credibility and security without downgrading efficiency. Empirical studies show that BASS outperforms other schemes in efficiency, model accuracy, and security.

Diverse technologies, such as machine learning and big data, have been driving the prosperity of the Internet of Things (IoT) and the ubiquitous proliferation of IoT devices. Consequently, it is natural that IoT becomes the driving force to meet the increasing demand for frictionless transactions. To secure transactions in IoT, blockchain is widely deployed since it can remove the necessity of a trusted central authority. However, the mainstream blockchain-based IoT payment platforms, dominated by Proof-of-Work (PoW) and Proof-of-Stake (PoS) consensus algorithms, face several major security and scalability challenges that result in system failures and financial loss. Among the three leading attacks in this scenario, double-spend attacks and long-range attacks threaten the tokens of blockchain users, while eclipse attacks target Denial of Service. To defeat these attacks, a novel bidirectional-linked blockchain (BLB) using chameleon hash functions is proposed, where bidirectional pointers are constructed between blocks. Furthermore, a new committee members auction (CMA) consensus algorithm is designed to improve the security and attack resistance of BLB while guaranteeing high scalability. In CMA, distributed blockchain nodes elect committee members through a verifiable random function. The smart contract uses Shamir’s secret-sharing scheme to distribute the trapdoor keys to committee members. To better investigate BLB’s resistance against double-spend attacks, an improved Nakamoto’s attack analysis is presented. In addition, a modified entropy metric is devised to measure eclipse attack resistance across different consensus algorithms. Extensive evaluation results show the superior resistance against attacks and demonstrate high scalability of BLB compared with current leading paradigms based on PoS and PoW.

With the widespread of 5G networks, the application of Federated Learning (FL) in Internet of Things (IoT) has become a trend. However, the trust problem caused by the centralized aggregation server, and the inefficiency problem caused by the low-performance devices, are still key challenges. Several studies involving asynchronous FL have been conducted to accelerate the training process, but they usually have a decreased model performance. In this paper, a blockchain-based asynchronous federated learning framework with a dynamic scaling factor is proposed. By adopting the blockchain, the trust problem among devices can be addressed. Meanwhile, the novel dynamic scaling factor is proposed to help improve the FL efficiency and accuracy. Extensive experiments are conducted on heterogeneous devices and the results show that the proposed framework mitigates the impact of low-performance devices while being as efficient as traditional FL with the extra benefit of alleviating the trust problem among IoT devices.