Intelligent connected vehicle fleet driven primarily by cloud data sharing is an efficient and energy-saving organizational model and demonstrates vast application potential in many scenarios. However, as the central hub for data sharing, the cloud platform's untrustworthiness poses severe challenges to the integrity and reliability of shared data. Existing auditing schemes fail to meet the low-latency, lightweight onboard computing, and succinct revocation demands of such fleets. Even with the application of batch auditing, the overall audit latency remains inadequately addressed. In this work, we propose an efficient auditing scheme called Drivora for cloud data sharing of intelligent connected fleet. We achieve secure delegated authenticator computation based on secret sharing and it requires only the master vehicle to perform the initial setup. Moreover, Drivora supports the aggregation of challenged blocks from multiple vehicles to produce a single integrity proof and it enables Drivora to handle multiple audit tasks from different vehicles at the same time. Furthermore, we propose a novel vehicle revocation mechanism. Different from traditional secret sharing-based approaches, Drivora requires only a single secret share to revoke multiple vehicles and achieves lower space complexity. We conduct extensive experimental evaluations of Drivora's performance and benchmark it against state-of-the-art approaches. Compared to conventional batch auditing, our scheme achieves a$2\times$-$107\times$improvement in auditing efficiency and reduces communication overhead by$2\times$-$939\times$. As the number of files increases, our overall auditing cost remains constant.

Sharding protocols in cryptocurrencies are dedicated to improving system throughput and reducing cross-shard transaction latency. However, they face the challenge of state explosion due to their stateful design. An intuitive solution is state sharding. Existing state sharding protocols aim to reduce the incidence of cross-shard transactions and balance transaction load. Nevertheless, it inevitably introduces the complex and sequential processing of cross-shard transactions and neglects the security of state data. To address these challenges, we propose SecChain, a secure stateless sharded blockchain via a novel state commitment in this paper. SecChain fully exploits the historical characteristics of transactions and designs the parallel cross-shard transaction execution based on asynchronous prepaid accounts. We then introduce a novel state commitment scheme to ensure the security of state data and improve the efficiency of transaction validation. In addition, we optimize the on-chain and off-chain storage by integrating an incremental partial state trie on-chain and a full trie with proofs off-chain. We perform a comprehensive evaluation using real-world workloads and results demonstrate that SecChain's throughput is 1.75× that of BrokerChain, and its latency is reduced by 7×. Furthermore, SecChain significantly reduces both proof overhead and storage overhead.

Federated learning (FL) as a distributed machine learning paradigm can be applied to edge intelligence scenarios for collaborative machine learning model building. Unfortunately, existing privacy-preserving FL applied to this scenario still faces three challenges: data heterogeneity, model heterogeneity, and privacy heterogeneity. Despite numerous privacy-preserving FL techniques proposed, they still cannot effectively address these three challenges. To solve this problem, we propose HeteroFed, a heterogeneous privacy-preserving FL framework for edge intelligence. Our HeteroFed contains heterogeneous model construction, dynamic gradient clipping, adaptive noise addition, and deviation-aware model aggregation. Specifically, we first use the heterogeneous model construction mechanism to enable personalized model training for different smart devices. Then, we propose a dynamic gradient clipping mechanism to perform dynamically adjusted gradient clipping on models uploaded by smart devices to limit the magnitude of gradients. Finally, we propose an adaptive noise addition mechanism to customize differential privacy protection for smart device models based on their convergence status. Furthermore, to mitigate the influence of noise perturbations on model performance, we propose a deviation-aware model aggregation mechanism for accurate model aggregation. Theoretical analysis demonstrates that HeteroFed achieves heterogeneous differential privacy. Extensive experiments show that HeteroFed outperforms similar methods, improving global model accuracy by 18%, 15%, 13%, and 18% on the MNIST, Fashion-MNIST, CIFAR-10, and THUCNews datasets, respectively.

Federated Learning (FL) enables collaborative model training while preserving data privacy, but it is highly vulnerable to backdoor attacks. Most existing defense methods in FL have limited effectiveness due to their neglect of the model's over-reliance on backdoor triggers, particularly as the proportion of malicious clients increases. In this paper, we propose FedBAP, a novel defense framework for mitigating backdoor attacks in FL by reducing the model's reliance on backdoor triggers. Specifically, first, we propose a perturbed trigger generation mechanism that creates perturbation triggers precisely matching backdoor triggers in location and size, ensuring strong influence on model outputs. Second, we utilize these perturbation triggers to generate benign adversarial perturbations that disrupt the model's dependence on backdoor triggers while forcing it to learn more robust decision boundaries. Finally, we design an adaptive scaling mechanism to dynamically adjust perturbation intensity, effectively balancing defense strength and model performance. The experimental results demonstrate that FedBAP reduces the attack success rates by 0.22%-5.34%, 0.48%-6.34%, and 97.22%-97.6% under three types of backdoor attacks, respectively. In particular, FedBAP demonstrates outstanding performance against novel backdoor attacks.

Industrial cloud storage systems enhance data availability and offer intelligent services to enterprises. However, they also bring significant concerns about data integrity since the cloud space provider may not consistently retain the outsourced data. Existing cloud storage verification methods impose a significant computational burden on edge devices, so they are unsuitable for industrial cloud storage systems. Although the light-weight homomorphic authenticator somewhat alleviates the computational load on the fog node, its effectiveness remains limited and it further complicates proof generation and verification. To address these problems, we propose Ascina, a new proof of retrievability framework for industrial cloud storage systems. We employ verifiable secret sharing to delegate tag computation tasks to the computing server without disclosing the signing key. Once the fog node completes its initial configuration, no further computations are required. Additionally, we propose the improved Ascina by utilizing Fast Fourier Transform (FFT) and Inverse Fast Fourier Transform (IFFT) technology to further alleviate the computational burden on the fog node. Furthermore, we propose a batch verification algorithm that simultaneously validates the integrity of multiple files while maintaining the same security assurances as single auditing. We evaluate the performance of Ascina through experiments and compare it with state-of-the-art methods. Experimental results demonstrate that the computational overhead on the fog node in Ascina is 5×-251× lower than that of Edasvic and our proof verification time and proof size are reduced by 5×-16× and 977×-3285×, respectively. As the size and quantity of files grow, Ascina demonstrates greater efficiency in both time and space.

In vector commitments, the complex process of generating and updating proofs, along with the large-sized proofs, seriously hinders the practicality of stateless cryptocurrencies. In this work, we present NTTproofs, containing two sub-schemes, a vector commitment (VC) and a mulit-vector commitment (MC). Both sub-schemes are maintainable and aggregatable, and they also enjoy fast openings (i.e., generating all the proofs) as well as efficient proof updates. MC in NTTproofs employs the Fast Number Theoretic Transform (NTT) and sharding technique to significantly improve the time of generating all proofs by up to$0.76 \times $and$0.32 \times $, respectively, over Balanceproofs, Matproofs. Moreover, our proposed MC in NTTproofs is efficiently maintainable and requires merely 15.78 milliseconds at$n_{1}=n_{2}=2^{12}$to update all proofs. Meanwhile, NTTproofs schemes exhibit superior aggregatability, taking 0.003 seconds in VC and 0.05 seconds in MC to aggregate 1024 proofs and reducing the size of an aggregated proof to a constant size of 96 Bytes. Finally, macrobenchmarks indicate that our proposed MC in NTTproofs outperforms the other schemes, but is slightly inferior to that of Balanceproofs.

Distributed federated learning models are vulnerable to Byzantine failures because malicious nodes can alter the training direction of the global model, making it deviate from normal training and rendering the global model unusable. To address this issue, we propose a defense scheme based on differential privacy and a Complex Accuracy-based multi-Krum Algorithm (DP-CAKA). First, we construct poisoning attacks against local models and conduct attack experiments using three Byzantine-robust federated learning methods. These experiments significantly increase the error rate of the global model, thereby demonstrating the vulnerability of distributed federated learning systems under Byzantine failures. Subsequently, we add noise to the local gradients using differential privacy to enhance privacy during the aggregation process. In addition, we design a Complex ACC-based Multi-Krum Algorithm (CAKA) that selects a few optimal local gradients to participate in the aggregation, thereby mitigating the negative impact of differential privacy on model accuracy. Experimental results demonstrate that DP-CAKA achieves an effective trade-off between privacy and availability, improving global model accuracy by 7.4% over Krum and Trimmed, and 1.5% over Median under poisoning attacks, by 20.7% over Krum and 0.5% over Median under Gaussian-attacks, and by 11.8% over Trimmed mean and 0.19% over Median under Sign-flipping attacks.

Existing multitask outsourcing computations struggle to guarantee the fairness for participants and the correctness of the computation results. Some solutions use blockchain to address the fairness issue in outsourcing computations. However, blockchain suffers from poor data privacy due to its public and transparent nature, as well as the latency because of limited scalability. To effectively confront these problems, we propose the Libras: a fair, secure, verifiable and scalable outsourcing computation scheme based on blockchain. In Libras, tasks are divided into multiple sub-task blocks, coupled with a deposit mechanism that enforces fairness throughout the process. Libras integrates a commitment mechanism with on-chain and off-chain collaboration for security, where the computation results are securely stored off-chain while proofs of these results are immutably recorded on-chain. Moreover, it employs a Directed Acyclic Graph (DAG)-based ledger architecture to significantly expedite transaction confirmations and facilitate elastic scalability. Furthermore, we devise a batch verification algorithm to simultaneously verify the accuracy of all computation results. Theoretical analysis and experiments demonstrate that Libras is fair, secure, verifiable, and scalable. The comparison results indicate that the verification time is 1.2× that of FVP-EOC.

Partial person re-identification (re-ID) refers to re-identify a person through occluded images. It suffers from two major challenges, i.e., insufficient training data and incomplete probe image. In this paper, we introduce a part-aware learning method for partial person re-identification. On the one hand, we adopt data augmentation operation to enrich the training data and improve the robustness of the model. On the other hand, we intuitively find that the partial person images usually have fixed percentages of parts, therefore, in partial person re-ID task, the probe image could be cropped from the pictures and divided into several different partial types following fixed ratios. Based on the cropped images, we propose the Cropping Type Consistency (CTC) loss to classify the cropping types of partial images. Moreover, in order to help the network better fit the generated and cropped data, we incorporate the Block Attention Mechanism (BAM) into the framework for attentive learning. To enhance the retrieval performance in the inference stage, we implement cropping on gallery images according to the predicted types of probe partial images. Through calculating feature distances between the partial image and the cropped holistic gallery images, the model can recognize the right person from the gallery. To validate the effectiveness of our approach, we conduct extensive experiments on the partial re- ID benchmarks and achieve state-of-the-art performance.