Deep hashing models have been widely adopted to tackle the challenges of large-scale image retrieval. However, these approaches face serious security risks due to their vulnerability to adversarial examples. Despite the increasing exploration of targeted attacks on deep hashing models, existing approaches still suffer from a lack of multimodal guidance, reliance on labeling information and dependence on pixel-level operations for attacks. To address these limitations, we proposed DiffHash, a novel diffusion-based targeted attack for deep hashing. Unlike traditional pixel-based attacks that directly modify specific pixels and lack multimodal guidance, our approach focuses on optimizing the latent representations of images, guided by text information generated by a Large Language Model (LLM) for the target image. Furthermore, we designed a multi-space hash alignment network to align the high-dimension image space and text space to the low-dimension binary hash space. During reconstruction, we also incorporated text-guided attention mechanisms to refine adversarial examples, ensuring them aligned with the target semantics while maintaining visual plausibility. Extensive experiments have demonstrated that our method outperforms state-of-the-art (SOTA) targeted attack methods, achieving better black-box transferability and offering more excellent stability across datasets.

Insulated Gate Bipolar Transistors (IGBTs) play a vital role in power electronics, producing large volumes of time-series data critical for fault detection and system health monitoring. The sheer data size challenges efficient storage and transmission, especially in IoT and edge computing scenarios. Conventional compression techniques, like wavelet transforms and PCA, often struggle to retain the complex, non-linear patterns in IGBT signals, leading to reduced reconstruction quality and impaired fault diagnosis. To overcome these issues, we introduce a novel Multi-Scale Residual Attention Generative Adversarial Network (MRA-GAN) tailored for IGBT data compression and reconstruction. The model features a generator with multi-scale convolutions, residual connections, and a spatiotemporal attention mechanism to effectively capture diverse signal characteristics. A discriminator ensures the reconstructed data closely mimics real IGBT signals through adversarial training. By balancing reconstruction accuracy and data realism, MRA-GAN achieves high compression ratios while preserving fault-related features. Evaluations show it outperforms traditional methods, supporting precise fault detection and enabling efficient data handling for real-time industrial monitoring. This approach significantly enhances data processing for IGBT applications, offering a scalable solution for power electronics diagnostics and resource-constrained environments.

Diagnosis of skin lesions based on imaging techniques remains a challenging task because data (knowledge) uncertainty may reduce accuracy and lead to imprecise results. This paper investigates a new deep hyperspherical clustering (DHC) method for skin lesion medical image segmentation by combining deep convolutional neural networks and the theory of belief functions (TBF). The proposed DHC aims to eliminate the dependence on labeled data, improve segmentation performance, and characterize the imprecision caused by data (knowledge) uncertainty. First, the SLIC superpixel algorithm is employed to group the image into multiple meaningful superpixels, aiming to maximize the use of context without destroying the boundary information. Second, an autoencoder network is designed to transform the superpixels' information into potential features. Third, a hypersphere loss is developed to train the autoencoder network. The loss is defined to map the input to a pair of hyperspheres so that the network can perceive tiny differences. Finally, the result is redistributed to characterize the imprecision caused by data (knowledge) uncertainty based on the TBF. The proposed DHC method can well characterize the imprecision between skin lesions and non-lesions, which is particularly important for the medical procedures. A series of experiments on four dermoscopic benchmark datasets demonstrate that the proposed DHC yields better segmentation performance, increasing the accuracy of the predictions while can perceive imprecise regions compared to other typical methods.

Manufacturing speed is one of the biggest challenges in 3D printing. Continuous stereolithography printing can effectively improve the printing speed. However, the model it can print is limited to the hollow out structure or flake structure. In the real application scenario, the models are the composition of multiple kinds of structures such as solid structure, hollow out structure, or flake structure. The continuous stereolithography printing scheme will not work for such models. We first propose a concept of maximum fillable distance (MFD) for a set of resin material and printing settings. And for a specific kind of printing setting, the MFD of resin material at different moving speeds is estimated by experiments. Furthermore, the max-min distance of each slice of the model is computed. And a printing control scheme to combining the continuous and layer-wise printing is generated automatically by comparing the max-min distance and MFD. Using the printing control scheme, two real models are successfully printed.

Distant supervised relation extraction has recently attracted researchers attention in the knowledge graph.However, the current feature encoding model of sentences can not fully represent the features in sentences, which poses a challenge.To solve this problem, we propose a two-dimensional feature encodingbased sentence-level attention model for relation extraction.In this model, we first employ bidirectional long short-term memory networks(BiLSTM) to capture the temporal dependency of the words in the sentence.Then we employ multi-dilated convolution to obtain the higher-level semantic units hidden in the sentence.Afterwards, we combine the above two-dimensional features to embed the encoding of sentences, which is expected to enhance the model's ability to express sentence features.Finally we build sentence-level attention to complete the relation extraction task.Compared with other excellent methods, the proposed approach provides a significant performance improvement.

In recent years, with the rapid development of mobile Internet and 5G technology, great changes have been brought to our lives, and human beings have stepped into the era of big data. These new features and techniques in 5G support many different types of mobile applications for users, which makes network security extremely challenging. Among them, more and more applications involve users’ private data, such as location information, financial information, and biological information. In order to prevent users’ privacy disclosure, most applications choose to use private protocols. However, such private protocols also provide a means for malware and malicious applications to steal users’ privacy and confidential data. From a more secure point of view, we need to provide a way for users to know how many private protocols are running on their mobile phones and distinguish which are authorized applications and which are not. Therefore, the analysis and identification of private protocols have become a hot topic in current research. How to extract the characteristics of network protocol effectively and identify the private protocol accurately becomes the most important part of this research. In this paper, we combine genetic algorithm and association rule algorithm and then propose a set of feature extraction algorithm and protocol recognition algorithm for unknown protocols. The experimental analysis based on the actual data shows that these methods can effectively solve the problems of feature extraction and recognition for unknown protocols and can greatly improve the accuracy of private protocol recognition.

Currently, the Internet of Things (IoT) provides individuals with real-time data processing and efficient data transmission services, relying on extensive edge infrastructures. However, those infrastructures may disclose sensitive information of consumers without authorization, which makes data access control to be widely researched. Ciphertext-policy attribute-based encryption (CP-ABE) is regarded as an effective cryptography tool for providing users with a fine-grained access policy. In prior ABE schemes, the attribute universe is only managed by a single trusted central authority (CA), which leads to a reduction in security and efficiency. In addition, all attributes are considered equally important in the access policy. Consequently, the access policy cannot be expressed flexibly. In this paper, we propose two schemes with a new form of encryption named multi-authority criteria-based encryption (CE) scheme. In this context, the schemes express each criterion as a polynomial and have a weight on it. Unlike ABE schemes, the decryption will succeed if and only if a user satisfies the access policy and the weight exceeds the threshold. The proposed schemes are proved to be secure under the decisional bilinear Diffie–Hellman exponent assumption (q-BDHE) in the standard model. Finally, we provide an implementation of our works, and the simulation results indicate that our schemes are highly efficient.

Summary In this big data era, service providers tend to put the data in a third‐party cloud system. Social networking websites are typical examples. To protect the security and privacy of the data, data should be stored in encrypted form. This brings forth new challenges: how to allow different users to access only the authorized part of the data without decryption of the data. Attribute‐based encryption (ABE) offers fine‐grained access control policy over encrypted data such that users can decrypt successfully only if their attributes satisfy the policy. However, one drawback of ABE is that the computational cost grows linearly with the complexity of ciphertext policy or the number of attributes. The situation becomes worse for mobile devices with limited computing resources. To solve this problem, we adopt the offline/online technique combining with the verifiable outsourced computation technique to propose a new ciphertext‐policy ABE scheme using bilinear groups in prime order, supporting the offline/online key generation and encryption, as well as the verifiable outsourced decryption. As a result, most computations of key generation and encryption can be executed offline, and the majority of computational workload in decryption can be outsourced to third parties. The scheme is selectively chosen‐plaintext attack‐secure in the standard model. We also provide the proof of verifiability on outsourced decryption. The simulation results show that our proposed scheme can effectively reduce the computational cost imposed on resource‐constrained devices. Copyright © 2016 John Wiley & Sons, Ltd.

Nowadays wireless sensor network (WSN) is widely used in human-centric applications and environmental monitoring. Different institutes deploy their own WSNs for data collection and processing. It becomes a challenging problem when institutes collaborate to do data mining while intend to keep data privacy on each side. Privacy preserving data mining (PPDM) is used to solve the above problem, which enables multiple parties owning confidential data to run a data mining algorithm on their combined data, without revealing any unnecessary information to each other. However, due to the huge amount of data collected and the complexity of data mining algorithms, it is preferable to outsource most of the computations to the cloud. In this paper, we consider a scenario in which two parties with weak computational power need jointly run a k-means clustering protocol, at the same time outsource most of the computation of the protocol to the cloud. As a result, each party can have the correct result calculated by the data from both parties with most of the computation outsourced to the cloud. As for privacy, the data owned by one party should be kept confidential from both the other party and the cloud.