With the widespread adoption of multi-view data in numerous fields, multi-view unsupervised feature selection (MUFS) has made notable strides in both feature pruning and missing-view completion. Nonetheless, existing MUFS methods typically rely on centralized servers, which cannot meet real-world demands for privacy preservation and distributed learning, and they often suffer from suboptimal solution and weak convergence guarantees. To address these challenges, IMUFFS, an incomplete multi-view unsupervised federated feature selection via cooperative particle swarm optimization (CPSO) and tensor-aligned learning (TAL) is proposed. Specifically, each client executes CPSO-TAL at two stages: (i) an external optimization phase that involves a CPSO, inspired by the co-evolutionary mechanism of hybrid breeding optimization algorithm, performing a global search in the feature space, and (ii) an internal optimization phase that leverages TAL with imputation and CP decomposition, where CP decomposition reduces dimensionality by decomposing the original tensor into a sum of core components, to learn low-dimensional embeddings, while simultaneously updating anchor graphs and view preference weights, thereby harmonizing imputation and representation learning. On the server side, a federated aggregation strategy using adaptive normalized mutual information (NMI) weighting combines the locally optimized feature selection (FS) weights and NMI scores from clients, ensuring privacy while improving the quality of FS and convergence. Extensive experiments on multiple datasets demonstrate that IMUFFS consistently outperforms state-of-the-art methods, yielding more effective and robust FS and enhancing better missing-view completion.

Face recognition (FR) brings convenience to peoples lives while also posing security risks. Some malicious users employ FR attacks to impersonate the identity of a target. To reveal the security risks, recent work has attacked black-box FR models by utilizing substitute models to generate adversarial face images that are misclassified as the target individual due to the attack transferability of substitute models. However, the substitute models cannot accurately approximate the target model that leads to a decrease in FR attack success rate and adversarial face image quality. To address the issue, we propose the PPOM-Attack, a substitute model-free Perturbation Prediction and Optimization Method for black-box adversarial Attack against face recognition. PPOM-Attack directly obtains feedback from the target model instead of using substitute models, it avoids any discrepancy with the attack objective. To achieve this goal, we design a proximal policy optimization (PPO)-based agent to predict the perturbation regions in the face image and self-adaptively disturb the regions. To maintain high-quality adversarial face images, we further propose a minimum brightness offsets method specifically designed to generate perturbations that minimize the feature embedding difference between the adversarial and targeted face images. The experimental results show that our approach outperforms state-of-the-art FR attack methods by an average of 21.7% in terms of attack success rate, while achieving better image quality on seven FR models.

The placement of analog Integrated Circuits (ICs) plays a critical role in their physical design. The objective is to minimize the Half-Perimeter Wire Length (HPWL) while satisfying complex analog IC constraints, such as symmetry. Unlike digital ICs, analog ICs are highly sensitive to parasitic effects, making device symmetry crucial for optimal circuit performance. However, existing methods, including both machine learning-based and analytical approaches, struggle to meet strict symmetry constraints. In machine learning-based methods, training a general model is challenging due to the limited diversity of the training data. In analytical methods, the difficulty lies in formulating symmetry constraints as a convex function, which is necessary for gradient-based optimization of the placement. To address the issue, we formulate the placement process as a Markov decision process and propose SACPlace, a multi-agent deep reinforcement learning method for Symmetry-Aware analog Circuit Placement. SACPlace initially extracts layout information and various constraints as the input information for placement refinement and evaluation. Subsequently, SACPlace constructs multi-agent policy networks for symmetry-aware placement by refining placement guided by the evaluation of optimal symmetry quality. Following this, SACPlace constructs multilayer perceptron-based critic networks to embed placement information for evaluating symmetry quality. This evaluation reward will be used for guiding placement refinement. Experimental results from four public analog ICs instances demonstrate that our method achieves the lowest actual wirelength and area while fully satisfying symmetry and common constraints, outperforming state-of-the-art methods. Additionally, simulation results on real-world analog ICs show better performance than these methods and even manual designs.

The automation of very large-scale PCB routing has long been an unresolved problem within the industry due to the variant electronic components and complex design rules. Existing automated PCB routing methods are primarily designed for single component (e.g., BGA, BTB, etc.) or for simple and small-scale PCBs, and often fail to meet the industry requirements for large-scale PCBs. The biggest challenge is to ensure nearly 100% routability and DRC compliance while achieving high efficiency for large-scale PCBs with various components. To address this challenge, we propose MegaRoute, a precise, efficient, and universal PCB routing method that surpasses the routing routability and DRC compliance of existing methods, including commercial tools, for PCBs with thousands of nets. MegaRoute introduces an adaptive step-size search algorithm that adjusts exploration steps based on design rules and surrounding obstacles, improving both routability and efficiency. We incorporate shape-based obstacle detection for strict DRC compliance and use routing optimization techniques to enhance routability. We conduct extensive experiments on hundreds of real-world PCBs, including mainboard PCBs with thousands of nets. The results show that MegaRoute achieves over 98% routability across all PCBs with DRC-free results, significantly outperforming the state-of-the-art methods and mainstream commercial tools.

Abstract The rapid advancement of large language models (LLMs) has opened up promising opportunities for their downstream applications in question-answering (QA), such as ChatGPT, ChatGLM, etc. However, such LLMs do not perform very well in domain-specific QA tasks without fine-tuning. But directly fine-tuning LLMs on domain-specific corpus data may lead to catastrophic forgetting, causing the LLMs to lose their general language capability. To address this problem, we propose the Knowledge-Enhanced Fine-Tuning (KEFT) method, an unsupervised fine-tuning approach to enhance the knowledge capability of LLMs in domain-specific QA tasks while preserving their general language capability. KEFT leverages the inherent language comprehension of pre-trained LLMs to generate synthetic-QA datasets from domain-specific corpus data autonomously for fine-tuning, and adopts a Low-Rank Adaptation (LoRA) method to further alleviate over-fitting. Furthermore, to enhance the representation of domain-specific knowledge, we introduce a knowledge-enhanced fine-tuning loss function, which encourages the model to learn the knowledge-question connection, thereby generating natural and knowledgeable answers. Our evaluations across multiple domain-specific datasets demonstrate that KEFT surpasses state-of-the-art fine-tuning approaches, enhancing the performance of various LLMs in QA tasks in both English and Chinese languages.

The Steiner minimum tree (SMT) serves as an optimal connection model for multiterminal nets in very large scale integration (VLSI). Constructing both rectilinear SMT (RSMT) and octilinear SMT (OSMT) are known to be NP-hard problems. Simultaneously, constructing multiple topologies of SMTs for a given net holds significant importance in alleviating routing constraints such as alleviating congestion and ensuring timing convergence. However, existing efforts predominantly focus on designing specialized methods to construct a specifically structured SMT for a given net, making it challenging to extend to different structures or topologies of SMTs, while also exhibiting insufficient optimization capabilities. In this work, we propose a unified approach based on deep reinforcement learning (DRL) to address both RSMT and OSMT problems while generating diverse routing topologies. First, we design an edge point sequence (EPS) that leverages the structural characteristics of SMT to connect the output of the deep learning model with the SMT structure. Second, we propose a deep learning model tailored for EPS, employing the negative wirelength of SMT as a reward to train the model using DRL. Third, we provide a corresponding rapid and accurate wirelength computation algorithm for evaluating the quality of the construction solution to expedite model training. Finally, we leverage the stochastic nature of machine learning to construct diverse SMT construction solutions. To the best of our knowledge, this is the first unified approach capable of simultaneously addressing both RSMT and OSMT problems while generating diverse solutions. The proposed unified approach demonstrates superior solution quality and higher efficiency compared to specifically designed algorithms.

Realistic co-speech gestures are important to anthropomorphize ECAs, as nonverbal behavior improves expressiveness of their speech greatly. However, the existing approaches to generating co-speech gestures with sufficient details (including fingers, etc.) in 3D scenarios are indeed rare. Additionally, they hardly address the problem of abnormal gestures, temporal–spatial coherence and diversity of gesture sequences comprehensively. To handle abnormal gesture issues, we put forward an angle conversion method to remove body part length from the original in-the-wild video dataset via transferring coordinates of human upper body key points into relative deflection angles and pitch angles. We also propose a neural network called HARP with encoder–decoder architecture to transfer MFCC featured speech audio into aforementioned angles on the basis of CNN and LSTM. The angles then can be rendered as corresponding co-speech gestures. Compared with the other latest approaches, the co-speech gestures generated by HARP are proved to be almost as good as the real person, i.e., they have strong temporal–spatial coherence, diversity, persuasiveness and credibility. Our approach puts finer control on co-speech gestures than most of the existing works by handling all key points of the human upper body. It is more feasible for industrial application, since HARP can be adaptive to any human upper body model. All related code and evidence videos of HARP can be accessed at https://github.com/drrobincroft/HARP .

In modern electronic manufacturing processes, multi-layer Printed Circuit Board (PCB) routing requires connecting more than hundreds of nets with perplexing topology under complex routing constraints and highly limited resources, so that takes intense effort and time of human engineers. PCB fanout as a pre-design of PCB routing has been proved to be an ideal technique to reduce the complexity of PCB routing by pre-allocating resources and pre-routing. However, current PCB fanout design heavily relies on the experience of human engineers, and there is no existing solution for PCB fanout automation in industry, which limits the quality of PCB routing automation. To address the problem, we propose a neuralized PCB fanout method by deep reinforcement learning. To the best of our knowledge, we are the first in the literature to propose the automation method for PCB fanout. We combine with Convolution Neural Network (CNN) and attention-based network to train our fanout policy model and value model. The models learn representations of PCB layout and netlist to make decisions and evaluations in place of human engineers. We employ Proximal Policy Optimization (PPO) to update the parameters of the models. In addition, we apply our PCB fanout method to a PCB router to improve the quality of PCB routing. Extensive experimental results on real-world industrial PCB benchmarks demonstrate that our approach achieves 100% routability in all industrial cases and improves wire length by an average of 6.8%, which makes a significant improvement compared with the state-of-the-art methods.

Cracks are one of the most common and significant types of road surface damage, posing a threat to the safety of pedestrians and vehicles. If left untreated, cracks can lead to severe consequences such as road and bridge collapse. Therefore, it is essential to develop an efficient road crack detection method. Traditional crack identification methods have the problem of being largely affected by the environment and having low recognition accuracy. In this paper, we propose a road crack detection model based on an improved You Only Look Once version 5 (YOLOv5) model that addresses the limitations of existing state-of-the-art crack detection methods in terms of accuracy and detection speed. First, we replace the intersection over union (IoU) loss function with the SCYLLA-IoU (SIoU) loss function for better accuracy. Second, to enhance detection performance, we replace the feature pyramid network (FPN) with a bi-directional feature pyramid network (BiFPN). Finally, to better extract spatial feature information of different sizes, we modify the original Spatial Pyramid Pooling-Fast (SPPF) module of YOLOv5 by using Spatial Pyramid Pooling Cross-Stage Partial Connections (SPPCSPC). We evaluated our YOLOv5s-BiFPN-SPPCSPC-SIoU (YOLOv5s-BSS) method on the dataset from the IEEE 2020 Global Road Damage Detection Challenge (GRDDC) and achieved promising results on road damage datasets from China, Japan, and the United States. The [email protected] of different cracks in three datasets reached 84.9%, 54.6%, and 71%. Our method outperforms related methods, with an increase of 0.7%, 0.7%, and 2.8% over YOLOv5s.

Abstract Attribute-based signature (ABS) allows signers with a set of attributes to sign messages anonymously using a specific signing policy. However, previous schemes suffer from some efficiency issues which are not widely applied on the blockchain. In this paper, we investigate ABS regarding its features and efficiency in the blockchain setting and provide our solution correspondingly. To solve the revocation problem of ABS in a more efficient manner, we introduce the update-free revocation function. Instead of the passive attribute expiration approaches, we take the active method to ensure that no parameter updates are required by users after the execution of the revocation function. In terms of efficiency, we first address the problem that the signer has to provide proof for all attributes in the predicate for privacy, which is one of the efficiency bottlenecks for ABS. By taking advantage of the blockchain architecture, we propose a new solution which can achieve the constant signature size and verification cost, while the signing cost can be greatly reduced. The corresponding security levels are satisfied according to their strict criteria. A generic construction as well as an instantiation are provided which is provably secure in the standard model satisfying the newly defined formal security definitions. Finally, a purer primitive is discussed.

Abstract With the outbreak of Covid‐19, both people's health and the world economy are facing great challenges. Contact tracing scheme based on Bluetooth of smartphones has been regarded as a viable way to mitigate the spread of Covid‐19. The existing schemes mainly belong to the centralized or the decentralized structure, both of which have their own limitations. It is infeasible for the existing schemes to balance the different demands of governments and users for user privacy and tracing efficiency at different periods of the epidemic. In this paper, we propose a hybrid contact tracing scheme named MLCT (multi‐level contact tracing scheme) which is mainly based on short group signature. MLCT provides multiple privacy levels by applying anonymous credential technology and secret sharing technology to desensitize user identity privacy and encounter privacy. Comparing to the previous schemes, MLCT fully considers the different demands of the government, patients, and close contacts for user privacy and tracing efficiency in the different stages of Covid‐19. The experimental results show viability in terms of the required resource from both server and mobile phone perspectives. And the security analysis demonstrates that MLCT can achieve the five targets security goals. It is expected that MLCT can contribute to the design and development of contact tracing schemes.

The Deepfake technique can swap the face of a person with the face of another person in an image or a video which may cause a public security problem. Recently, researchers have focused on detecting deepfake images by deep learning. However some recent works have observed that detectors trained on images produced by one deepfake model perform poorly when tested on others. In this paper we propose to detect deepfake images through heterogeneous feature ensemble learning. We first extract gray gradient features, spectrum features and texture features from real and fake face images, then integrate them into an ensemble feature vector through a flatten process, and finally adopt a back-propagation neural network to train a deepfake detector with the feature vector. Experimental results show that our approach achieves better detection accuracy compared with several state-of-the-art deepfake detectors.

With the proliferation of cloud computing, data owners can outsource the spatial data from the Internet of Things devices to a cloud server to enjoy the pay-as-you-go storage resources and location-based services. However, the outsourced services may raise privacy concerns, since the cloud server may not be fully trusted for both data owners and search users. If the data owners and search users conventionally encrypt the spatial data and query requests, the efficiency and functionality of query processing are weakened. Most of the existing works only focus on spatial data search or keyword search and do not consider spatial keyword search over encrypted data. In this article, we first design a geometric range query (GRQ) scheme, which can generate an arbitrary geometric range to fit the search user’s desired spatial data while protecting location privacy. Furthermore, based on GRQ, we propose a multidimensional spatial keyword similarity search scheme with access control (MSSAC) by integrating the polynomial function and matrix transformation. Specifically, an access control strategy is defined by a role-based polynomial function, which is embedded in the vectors of indices and trapdoors to achieve efficient and lightweight access control. Moreover, MSSAC enables the cloud server to execute compute-then-compare operations for spatial keyword search in a privacy-preserving manner by leveraging techniques of randomizable permutation and matrix multiplication. The formal security analyses and extensive experiments demonstrate that GRQ and MSSAC preserve the privacy of data owners and search users while achieving efficient spatial keyword search.

Cloud storage services allow data owners to outsource their potentially sensitive data (e.g., private genome data) to remote cloud servers in a ciphertext form. To enable data owners to further share the data encrypted in ciphertexts, many proxy re-encryption (PRE) schemes are proposed. However, most schemes only support single-recipient or coarse-grained re-encryption, which may limit the flexibility for data sharing. To address this issue, we propose a Policy-based Broadcast Access Authorization (PBAA) scheme by introducing the well-established identity-based broadcast encryption (IBBE) and key-policy attribute-based encryption into PRE. In our PBAA scheme, a data owner can apply IBBE to encrypt his data to a group of recipients. More importantly, the data owner can generate a delegation key with an access policy, and send this key to the cloud such that it can convert any initial ciphertext satisfying the access policy into a new ciphertext for a new group of recipients. With these features, cloud users can share their remote data in a secure and flexible way. Security analysis and performance evaluation show that the PBAA scheme is secure and efficient, respectively.

In Industry 5.0, the massive number of Internet of Things devices have increasing demands for group communication with a high communication efficiency and low energy consumption. However, group communication meets continuously increasing security risk challenges. Existing authentication and group key agreement schemes have encountered many problems, such as lack of anonymity and untraceability. In this article, we propose an anonymous authentication and dynamic group key agreement scheme based on the Blockchain and token mechanism, where each group member can apply for a time-sensitive token during the first authentication and only needs to check the validity of the token in the subsequent authentication, reducing the computational and transmission costs considerably. The verification on the security of the proposed scheme is tackled through mathematical analysis and validated using ProVerif, and comparisons with existing schemes demonstrate that the proposed scheme reduces the security risks and each group member’s energy consumption.

Secure search techniques over encrypted cloud data allow an authorized user to query data files of interest by submitting encrypted query keywords to the cloud server in a privacy-preserving manner. However, in practice, the returned query results may be incorrect or incomplete in the dishonest cloud environment. For example, the cloud server may intentionally omit some qualified results to save computational resources and communication overhead. Thus, a well-functioning secure query system should provide a query results verification mechanism that allows the data user to verify results. In this paper, we design a secure, easily integrated, and fine-grained query results verification mechanism, by which, given an encrypted query results set, the query user not only can verify the correctness of each data file in the set but also can further check how many or which qualified data files are not returned if the set is incomplete before decryption. The verification scheme is loose-coupling to concrete secure search techniques and can be very easily integrated into any secure query scheme. We achieve the goal by constructing secure verification object for encrypted cloud data. Furthermore, a short signature technique with extremely small storage cost is proposed to guarantee the authenticity of verification object and a verification object request technique is presented to allow the query user to securely obtain the desired verification object. Performance evaluation shows that the proposed schemes are practical and efficient.

Evolutionary Algorithms (EA) are widely applied in Neural Architecture Search (NAS) and have achieved appealing results. Different EA-based NAS algorithms may utilize different encoding schemes for network representation, while they have the same workflow. Specifically, the first step is the initialization of the population with different encoding schemes, and the second step is the evaluation of the individuals by the fitness function. Then, the EA-based NAS algorithm executes evolution operations, e.g., selection, mutation, and crossover, to eliminate weak individuals and generate more competitive ones. Lastly, evolution continues until the max generation and the best neural architectures will be chosen. Because each individual needs complete training and validation on the target dataset, the EA-based NAS always consumes significant computation and time inevitably, which results in the bottleneck of this approach. To ameliorate this issue, this article proposes a distributed framework to boost the computation of the EA-based NAS algorithm. This framework is a server/worker model where the server distributes individuals requested by the computing nodes and collects the validated individuals and hosts the evolution operations. Meanwhile, the most time-consuming phase (i.e., individual evaluation) of the EA-based NAS is allocated to the computing nodes, which send requests asynchronously to the server and evaluate the fitness values of the individuals. Additionally, a new packet structure of the message delivered in the cluster is designed to encapsulate various network representations and support different EA-based NAS algorithms. We design an EA-based NAS algorithm as a case to investigate the efficiency of the proposed framework. Extensive experiments are performed on an illustrative cluster with different scales, and the results reveal that the framework can achieve a nearly linear reduction of the search time with the increase of the computational nodes. Furthermore, the length of the exchanged messages among the cluster is tiny, which benefits the framework expansion.

With the proliferation of cloud services, cloud-based image retrieval services enable large-scale image outsourcing and ubiquitous image searching. While enjoying the benefits of the cloud-based image retrieval services, critical privacy concerns may arise in such services since they may contain sensitive personal information. In this paper, we propose an efficient and Privacy-Preserving Image Retrieval scheme with Key Switching Technique (PPIRS). PPIRS utilizes the inner product encryption for measuring Euclidean distances between image feature vectors and query vectors in a privacy-preserving manner. Due to the high dimension of the image feature vectors and the large scale of the image databases, traditional secure Euclidean distance comparison methods provide insufficient search efficiency. To prune the search space of image retrieval, PPIRS tailors key switching technique (KST) for reducing the dimension of the encrypted image feature vectors and further achieves low communication overhead. Meanwhile, by introducing locality sensitive hashing (LSH), PPIRS builds efficient searchable indexes for image retrieval by organizing similar images into a bucket. Security analysis shows that the privacy of both outsourced images and queries are guaranteed. Extensive experiments on a real-world dataset demonstrate that PPIRS achieves efficient image retrieval in terms of computational cost.

Malware detection has become mission sensitive as its threats spread from computer systems to Internet of things systems. Modern malware variants are generally equipped with sophisticated packers, which allow them bypass modern machine learning based detection systems. To detect packed malware variants, unpacking techniques and dynamic malware analysis are the two choices. However, unpacking techniques cannot always be useful since there exist some packers such as private packers which are hard to unpack. Although dynamic malware analysis can obtain the running behaviours of executables, the unpacking behaviours of packers add noisy information to the real behaviours of executables, which has a bad affect on accuracy. To overcome these challenges, in this paper, we propose a new method which first extracts a series of system calls which is sensitive to malicious behaviours, then use principal component analysis to extract features of these sensitive system calls, and finally adopt multi-layers neural networks to classify the features of malware variants and legitimate ones. Theoretical analysis and real-life experimental results show that our packed malware variants detection technique is comparable with the the state-of-art methods in terms of accuracy. Our approach can achieve more than 95.6\% of detection accuracy and 0.048 s of classification time cost.

Malware detection becomes mission critical as its threats spread from personal computers to industrial control systems. Modern malware generally equips with sophisticated anti-detection mechanisms such as code-morphism, which allows the malware to evolve into many variants and bypass traditional code feature based detection systems. In this paper, we propose to disassemble binary executables into opcodes sequences, and then convert the opcodes into images. By comparing the opcode images generated from binary targets with the opcode images generated from known malware sample codes, we can detect if the target binary executables contain variants of these known malwares. Theoretical analysis and real-life experiments results show that malware detection using visualized analysis is comparable in terms of accuracy, our approach can significantly improve 15\% of detection accuracy when the detection set contains a large quantity of binaries and the training set is small.

Recently, secure search over encrypted cloud data has become a hot research spot and challenging task. Some secure search schemes have been proposed to try to meet this challenge. In this paper, we propose a conjunctive multi-keyword secure search scheme for multiple data owners. To guarantee data security and system flexibility in the multiple data owners environment, we design an ingenious secure query scheme that allows each data owner to adopt randomly chosen temporary keys to build secure indexes for different data files. An authorized data user does not need to know these temporary keys of constructing indexes and can instead randomly choose another temporary query keys to encrypt query keywords while the cloud can correctly perform keywords matching over encrypted data files. Extensive experiments demonstrate the correctness and practicality of the proposed scheme.

Malware detection becomes mission critical as its threats spread from personal computers to industrial control systems. Modern malware generally equips with sophisticated anti-detection mechanisms such as code-morphism, which allows the malware to evolve into many variants and bypass traditional code feature based detection systems. In this paper, we propose to disassemble binary executables into opcodes sequences, and then convert the opcodes into images. By using convolutional neural network to compare the opcode images generated from binary targets with the opcode images generated from known malware sample codes, we can detect if the target binary executables is malicious. Theoretical analysis and real-life experiments results show that malware detection using visualized analysis is comparable in terms of accuracy, our approach can significantly improve 15% of detection accuracy when the detection set contains a large quantity of binaries and the training set is much smaller.