Accurate traffic flow prediction plays a pivotal role in intelligent transportation systems (ITS). While deep learning-based approaches have demonstrated remarkable success in this domain, their performance heavily depends on the availability of large-scale training data. However, many cities face challenges in collecting sufficient traffic flow data due to privacy concerns and substantial storage requirements. Consequently, conventional traffic flow prediction models often suffer from performance degradation when applied to cities with limited data availability, primarily due to spatially unbalanced data distributions. To overcome this limitation, we propose a novel pre-trained framework for cross-city traffic flow prediction, termed PTCC. Different from existing methods that focus solely on optimizing performance for data-rich cities, our framework innovatively transfers spatiotemporal knowledge from data-abundant cities to enhance prediction accuracy in data-scarce scenarios. The proposed PTCC framework comprises three key components: 1) A pre-trained module that learns long-term temporal patterns from traffic flow data in source cities and generates comprehensive segment-level representations; 2) A discrete graph learning structure that captures node dependencies from contextual segment-level representations; 3) A spatiotemporal prediction module that effectively transfers the acquired knowledge to facilitate accurate traffic flow forecasting in target cities. We conduct extensive experiments to validate the framework’s effectiveness, training the model on METR-LA and PEMS-BAY datasets, and evaluating its performance on PEMS04 and PEMS08 datasets. The experimental results demonstrate that our pre-trained frame-work significantly outperforms existing methods, establishing its superiority for traffic flow prediction in cities with limited data availability.

Anonymous credentials are an essential cryptography primitive to protect user privacy and provide fine-grained access control for proving ownership and rights of specific credentials. There are currently two roadmaps to designing anonymous credentials: one is signature credentials, which are constructed by signature with efficient protocols and non-interactive zero-knowledge proofs, and the other is functional credentials, which are transformed from predicate encryption schemes. However, none of the existing instances of anonymous credentials support$expressive$access policies expressed as conjunction, disjunction, or arbitrary Boolean formulas, which are particularly useful for cloud services. In this paper, we propose a new fast and expressive anonymous credential, called FEAC. It is constructed with the unique$dual$$randomness$$splitting$technique, which combines the most efficient anonymous key-policy attribute-based encryption (USENIX 24) and short randomizable signature (CT-RSA 18) to balance efficiency, expressiveness, and security, demonstrating a new way to instantiate anonymous credentials. Furthermore, our credential presentation protocol offloads most of the time-consuming computation to the cloud server (11 pairing) to reduce the computational burden on the user side (2 pairing). We propose formal definitions and formal security proofs of FEAC. We provide implementations and evaluate the performance of FEAC, comparing it to state-of-the-art work.

Incentive (or point) systems are widely deployed across industries such as retail, tourism, and finance to enhance customer loyalty and create benefits for service providers. However, their operation typically requires the collection and processing of sensitive customer data, leading to significant privacy concerns. Existing privacy-preserving incentive systems predominantly rely on bilinear pairings and the discrete logarithm assumption, which, while efficient in classical settings, are vulnerable to quantum adversaries and thus lack long-term security guarantees. To address this limitation, we present LatInc, a practical lattice-based privacy-preserving incentive system. LatInc integrates state-of-the-art lattice-based signatures with efficient protocols, the ABDLOP commitment, and efficient lattice zero-knowledge proofs, achieving a robust balance between post-quantum security and efficiency. Relying on the hardness of the MLWE and MSIS problems, we formally prove that LatInc achieves unforgeability, anonymity, and framing-resistance in the random oracle model. We implement a demo of the system and evaluate its performance on a standard laptop platform. Experimental results show that the communication overheads for the Earning and Spending protocols are approximately 99 KB and 140 KB, respectively, with execution times of 610 ms and 900 ms, highlighting significant efficiency gains over previous lattice-based incentive constructions.

In a scenario where an issuer wishes to issue an attribute-based anonymous credential to a user, this issuance is conditional on a number of real-world outcomes. These outcomes involve multiple entrusted oracles confirming the occurrence of several events, after which the issuance can proceed successfully. Such contractual credentials can serve as an important building block for blockchain-based Web 3.0 systems and can be used in real-world applications that require privacy-preserving, prescheduled authorization. However, there is currently no work that enables the pre-issuance of credentials based on oracles and events. In this work, we propose contractual anonymous credentials, called FlyCred, to fill this gap. With FlyCred, the issuer can issue an encrypted credential to a user, controlled by a dual-layer authorization policy consisting of oracle-based and event-based expressive policies. As core building blocks, we introduce two novel cryptographic primitives: the Adaptor Anonymous Credential and ABE-based Signature Witness Encryption with Tags, which can serve as independent interests. We provide efficient instantiations of these primitives and evaluate their performance under different security levels and system parameters on a laptop, showing that the computation and communication overhead of the credential pre-issuance is less than 85.8 seconds and 8.7 MB, respectively.

Object detection plays an important role in areas such as intelligent surveillance and autonomous driving but is also faces the threat of adversarial patch attacks. Because adversarial patch attacks are highly stealthy, efficient and physically realizable, they pose a huge security risk to real-world object detectors. Therefore, we propose a segmented defense method, Localization and Elimination (LAE), for physically realizable adversarial patch attacks. The method designs three localization modules, namely, image information segmentation, heterogeneous region extraction, and local region preservation, as well as a feature fusion module, by analyzing the three intrinsic features of adversarial patches. By fusing the feature maps output from the three localization modules, the patch region feature map is finally output through the feature fusion module. Then the localized patch regions are filled with black pixels. This approach is different from other defense methods in that it can provide excellent defense performance against physically adversarial patches of different sizes, numbers, locations, and appearances in a variety of complex environmental contexts. We have demonstrated through extensive experiments that this defense method provides excellent defense performance and greater robustness than current state-of-the-art defense methods.

Malware can greatly compromise the integrity and trustworthiness of information and is in a constant state of evolution. Existing feature fusion‐based detection methods generally overlook the correlation between features. And mere concatenation of features will reduce the model’s characterization ability, lead to low detection accuracy. Moreover, these methods are susceptible to concept drift and significant degradation of the model. To address those challenges, we introduce a feature graph‐based malware detection method, malware feature graph (MFGraph), to characterize applications by learning feature‐to‐feature relationships to achieve improved detection accuracy while mitigating the impact of concept drift. In MFGraph, we construct a feature graph using static features extracted from binary PE files, then apply a deep graph convolutional network to learn the representation of the feature graph. Finally, we employ the representation vectors obtained from the output of a three‐layer perceptron to differentiate between benign and malicious software. We evaluated our method on the EMBER dataset, and the experimental results demonstrate that it achieves an AUC score of 0.98756 on the malware detection task, outperforming other baseline models. Furthermore, the AUC score of MFGraph decreases by only 5.884% in 1 year, indicating that it is the least affected by concept drift.

Malware is proliferating at an exponential rate in cyberspace, posing serious threats to on-device systems characterized by limited computational capabilities. In this work, we address the critical challenge posed by data imbalance—where rare malware families receive inadequate representation—by proposing MalViT, a lightweight Vision Transformer (ViT) architecture that directly operates in the JPEG frequency domain. Rather than converting Huffman-coded signals into RGB spatial images, MalViT leverages Discrete Cosine Transform (DCT) coefficients to reduce data redundancy and computational overhead. We further improve the model’s generalization through both pre-training and fine-tuning workflows. Comprehensive evaluations on two large-scale, real-world malware datasets, MalNet-Image (1.26 M samples) and BODMAS (51 K samples), demonstrate that MalViT accelerates data loading by nearly threefold compared to existing methods. On GPU and CPU, MalViT achieves approximately 2.0× and 4.7× faster inference throughput than MobileViT, respectively, while incurring minimal or even improved accuracy loss. When processing 224 × 224-pixel JPEG images, MalViT completes inference within an average of 3.12ms per sample, which is 8.79× faster than VisMal and 5.91× faster than ViT4Mal. Furthermore, its compact design comprises only 1.1M parameters and requires 10M MACs, making it particularly suitable for resource-constrained on-device deployment.

Smart contracts and blockchain mutually reinforce each other, leveraging their core attribute of decentralized interoperability to play crucial roles in both on-chain code and off-chain data. Nonetheless, this dual-edged nature, characterized by immutability once deployed and an immature language ecosystem, introduces significant risks. Consequently, smart contract vulnerabilities have emerged as a major security threat within trusted blockchain environments. With the exponential growth in the number of smart contracts, traditional detection methods necessitate considerable data overhead. On the other hand, the growing complexity of code semantic relationships and the cumulative error effects of conventional detection techniques further compound the issue. To address these challenges and enhance the learning capability for complex semantic relationships, we proposed a novel deep learning approach: Multi-Level Attention Graph Neural Network (ML-AGNN). This method integrates adaptive attention mechanisms and channel aggregation within a message passing neural network, effectively tackling the limitations of local semantic information and inaccuracies in modeling semantic information due to deeper network layers. We have implemented this approach in a prototype named GNN and validated it using over 40,000 smart contracts from Ethereum. Our extensive results demonstrated that this solution achieves an accuracy of 91.77%and a recall of 87.17% in detecting reentrancy vulnerabilities, significantly surpassing state-of-the-art methods. Additionally, another experiment confirms that our approach markedly outperforms contemporary methods in detecting timestamp dependency vulnerabilities.

Federated learning (FL) is vulnerable to data poisoning attacks when an adversary attempts to upload poison gradients with the intent to corrupt the global model of FL. Various approaches have been proposed to counter these risks. However, it becomes challenging when one tries to preserve the privacy of FL participants and ensure robustness against data poisoning attacks. In this paper, we propose DPFLA, a novel scheme that can detect poisoning attacks without revealing the actual gradients of participants. DPFLA is a lossless aggregation scheme delicately designed for adopting masks to protect private data while extracting poisoned data features. Specifically, we first apply removable masks to the gradients outputted by each participant. Second, we aggregate the masked data and decompose them using Singular Value Decomposition (SVD) to extract specific features as well as achieve dimensionality reduction. Third, we leverage a clustering paradigm to detect poison gradients from the low dimension and eliminate them in the following training rounds. We conducted extensive experiments to demonstrate that DPFLA can detect poison gradients effectively. Additionally, the comparisons of case studies demonstrate that DPFLA outperforms the state-of-the-art methods.

Combining Graph neural networks (GNNs) with contrastive learning for anomaly detection has drawn rising attention recently. Existing graph contrastive anomaly detection (GCAD) methods have primarily focused on improving detection capability through graph augmentation and multi-scale contrast modules. However, the underlying mechanisms of how these modules work have not been fully explored. We dive into the multi-scale and graph augmentation mechanism and observed that multi-scale contrast modules do not enhance the expression, while the multi-GNN modules are the hidden contributors. Previous studies have tended to attribute the benefits brought by multi-GNN to the multi-scale modules. In the paper, we delve into the misconception and propose Multi-GNN and Augmented Graph contrastive framework MAG, which unified the existing GCAD methods in the contrastive self-supervised perspective. We extracted two variants from the MAG framework, L-MAG and M-MAG. The L-MAG is the lightweight instance of the MAG, which outperform the state-of-the-art on Cora and Pubmed with the low computational cost. The variant M-MAG equipped with multi-GNN modules further improve the detection performance. Our study sheds light on the drawback of the existing GCAD methods and demonstrates the potential of multi-GNN and graph augmentation modules. Our code is available at https://anonymous.4open.science/r/MAG-Framework-74D0.

Deep hashing is frequently utilized in large-scale image retrieval because of its strong representation learning capabilities and effective processing capacity. However, deep hashing models are susceptible to adversarial examples. We propose a label-guided weighted autoencoder network (LGWAE) to generate adversarial examples for targeted hashing attacks. Specifically, we first introduce a multi-label learning network to extract the semantic features and the category code of different labels. Then, the semantic features and the benign image are collectively fed into an autoencoder in order to generate a natural-looking adversarial example. The category code is used as target hash code to supervise the generation of the adversarial example. To efficiently generate better-performing adversarial examples, we design a weighted Hamming distance loss that dynamically adjusts the loss value based on the label similarity between the benign image label and the target label. Numerous experiments demonstrate that we are capable of efficiently and effectively generating better quality adversarial samples.

Current specific emitter identification methods based on deep learning face many challenges such as high computational effort, weak anti-interference capability, unstable signal feature extraction, and limited improvement in classification performance. To solve these challenges, a new deep learning method is proposed, namely Deep Residual Shrinking Networks with Simple Parameter-Free Attention Module (DRSN-SimAM). The advantages of the parameter-free attention module and deep residual shrinkage network are integrated by DRSN-SimAM. The parameter-free attention module is introduced into the residual shrinkage building unit for adaptively learning thresholds, filtering out redundant information irrelevant to the signal fingerprint. We used the simple parameter-free attention module to enhance the ability of the model to learn features in strong noisy signals, with the goal of improving the classification of wireless devices. Experimental results reveal that the classification accuracy is as high as 98.8%. The number of parameters of the proposed DRSN-SimAM is 12.29% less than the number of parameters of the DRSN when the number of units is 11. Our proposed DRSN-SimAM is more effective in terms of improved wireless device identification performance and model size compression as compared to existing specific emitter identification methods based on deep learning.

In modern times, people have paid more attention to their private information. The data confidentiality is very important in many economic aspects. In this paper, we proposed a secure auction system, in which the bids will not be revealed, and no one can fake the winning identity and the winner cannot change the winning bid. The communication cost of our scheme is low; only two rounds communication are needed between the bidders and the auctioneer. And we show that our scheme achieves the desired security requirements.