As artificial intelligence continues to drive advancements in computer vision, particularly in areas such as image analysis, object detection, and facial recognition, the ability to accurately recognize patterns in visual data has become a central focus of research. However, alongside these advances, concerns about the privacy risks associated with the training data used in AI models have also gained prominence. Deep learning models, frequently employed in computer vision tasks, can unintentionally expose sensitive information from the data they are trained on, raising the need for comprehensive research into privacy-preserving techniques. This paper explores the intersection of AI-driven pattern recognition and the privacy risks involved in training models on image data. Existing studies show that attackers can exploit the gradients from deep learning processes to reconstruct original image data, including personal and identifiable information, such as facial features. By iteratively adjusting input data, attackers can minimize the difference between the gradients of the random and stolen data, leading to the full reconstruction of private images. Current privacy protection methods fall short of explaining the relationship between an attacker’s capacity to recover visual data and the structure of the targeted model. This paper introduces a novel privacy auditing framework that directly assesses the extent to which gradient-based attacks can reconstruct sensitive data. Unlike traditional methods, which mainly focus on mitigating privacy risks through model regularization or data obfuscation, our approach provides a systematic and quantitative evaluation of gradient leakage, filling a critical gap in existing privacy protection techniques. This paper investigates the relationships among reconstructed data, model gradients, and the original input data in the context of computer vision. By formalizing the connection between gradient similarity and data similarity, we propose a novel methodology that quantifies the vulnerability of deep learning models to data reconstruction attacks. Building on these insights, we propose a novel privacy auditing method aimed at evaluating the privacy risks associated with deep learning models used in pattern recognition for image data.

For the creation of wireless network applications, node locations are frequently necessary. However, communication effectiveness, measurement accuracy, and localization stability will be low in irregular multi-hop networks when locating nodes using conventional algorithms. To this end, a novel cooperative localization algorithm using expected minimum segments (LEMS, for short) is proposed in this paper. LEMS begins by measuring the distance between paired nodes, which is completed along with network initialization. Then, each unlocated node constructs its own sub-network, including it, based on the error characteristics among anchor nodes. Finally, each unlocated node searches for its estimated location in its sub-region based on the objective function generated by the chaotic mapping. Simulation results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art regarding efficiency, accuracy, and stability for various irregular networks. Specifically, our proposed algorithm achieves a median improvement in localization accuracy of 0.62 to 29.57 times and a reduction in the range of localization errors of 0.06 to 16.8 times.

The emergence of blockchain-based cryptocurrencies, such as Bitcoins, has presented a promising alternative for e-payment methods, owing to their unique features of decentralization and anonymity. The usage of these currencies has grown exponentially, particularly in anonymous e-payment and without any trusted third party. However, the decentralized and anonymous nature of these currencies has also resulted in misbehaviors, e.g., money laundering. Therefore, detecting transaction misbehaviors has garnered increasing attention. In this paper, we propose TMAS, a transaction misbehavior analysis scheme for blockchain-based cryptocurrencies. We propose various transaction analysis approaches, feature extraction algorithms, and detection models for misbehaviors, including money laundering. We have implemented a real experimental system to detect misbehaviors, including money laundering, in blockchain-based cryptocurrencies such as Bitcoins. The proposed system includes ten features in the transaction graph, two heuristic money laundering models, and an analysis method for account linkage, which identifies accounts that are distinct but controlled by an identical entity. To verify the effectiveness of our proposed indicators and models, we have analyzed a sample of 100M transactions and computed transaction features, leading to the identification of some suspicious accounts. Moreover, the proposed methods can be applied to other cryptocurrencies, no matter token-based such as Bitcoins or account-based such as Ethereum.

Cloud data auditing is essential to ensure the integrity of cloud data.The main idea of cloud auditing is to entrust the audit task to a thirdparty auditor (TPA) with powerful computing ability.However, TPA may lead to data leakage and become the single point of failure.Recently, blockchain has been introduced to solve these problems by TPA.However, the dynamic storage structure developed by traditional cloud storage does not apply to the blockchain.This paper proposes a blockchain-based collaborative public auditing scheme for dynamic data.We design the cloud service provider(CSP) to generate a challenge set using the latest block hash.It does not need to interact with the blockchain in the challenge phase, dramatically reducing communication overhead.In addition, considering economic factors, we allow users to seek partners to reduce audit costs.The EigenTrust model evaluates the reputation of each user's audit behaviour, effectively avoiding the probability of malicious users participating.For data update, we introduce the Pseudo Index Linked List(PIL) index management structure, which reduces the size of the index management structure to adapt to the blockchain's characteristics and makes the update operation have a constant time complexity.Through a complete security analysis and performance evaluation, we proved the security and effectiveness of the scheme.

In this paper, we consider two kinds of quaternary sequences, i.e., quaternary classical cyclotomic sequences with period q where q is an odd prime, and quaternary Ding-Helleseth generalized cyclotomic sequences with period pq where p is odd prime distinct from q. Then, using the generalized "Gauss periods", we derive 4-adic complexity of these sequences for any p,q and the results show that they have high symmetric 4-adic complexity.

Data deduplication can solve the problem of resource wastage caused by duplicated data. However, due to the limited resources of Internet of Things (IoT) devices, applying data deduplication to IoT scenarios is challenging. Existing data deduplication frameworks for the IoT are prone to inefficiency or trust crises due to the random allocation of edge computing nodes. Furthermore, side-channel attacks remain a risk. In addition, after IoT devices store data in the cloud through data deduplication, they cannot share their data efficiently. In this paper, we propose a secure and efficient data deduplication framework for the IoT based on edge computing and blockchain technologies. In this scheme, we propose a model based on parallel use of three-layer and two-layer architectures and introduce the RAndom REsponse (RARE) scheme to resist side-channel attacks. We also design a label tree to realise one-to-many data-sharing, which improves efficiency and meets the needs of the IoT. In addition, we use blockchain to resist collusion attacks. Experiments were conducted to demonstrate that our framework has advantages over similar schemes in terms of communication cost, security and efficiency.