Retrieving visual content from electroencephalography (EEG) signals represents a challenging frontier in implicit multimedia analysis, yet it suffers from extreme modal heterogeneity. The high-dimensional, non-stationary noise in neural signals limits conventional point-to-point similarity measures in capturing complex semantic manifolds. To bridge this gap, we propose the Neuro-Image Geometric Contrastive Learning (NIGCL) framework. Departing from reliance solely on simple first-order similarity metrics, NIGCL employs a geometry-aware alignment mechanism rooted in manifold learning. Specifically, we incorporate a Geometric Area Contrastive Loss based on the Gram matrix determinant, which constrains the geometric area of cross-modal feature pairs to enforce intra-class compactness and mitigate the impact of orthogonal perturbations. This global constraint is complemented by a local dot-product objective for fine-grained consistency. Additionally, we propose Geometric Area Ranking (GaR) to replace standard ranking protocols, identifying semantically consistent images via the geometric area in high-dimensional spaces. Experiments on the THINGS-EEG dataset show that NIGCL achieves superior performance, attaining 31.2% Top-1 and 61.6% Top-5 accuracy in 200-way retrieval. Reconstruction evaluations further confirm that our geometrically-aligned representations significantly improve semantic fidelity over traditional methods. This framework offers a novel perspective on aligning highly heterogeneous multimedia data through explicit geometric constraints.

Automatic code summarization, also known as code comment generation, has been proven beneficial for developers to understand better and maintain software projects. However, few research works have investigated the robustness of such models. Robustness requires that the model sustains the quality of the output summaries in the presence of perturbations to the inputs. In this paper, we provide an in-depth study of the robustness of code summarization models. We propose CREATE (Code summaRization modEl’s Adversarial aTtackEr), an approach for performing adversarial attacks against the model. This approach can generate adversarial samples to mislead the model and explore its robustness while ensuring these samples are compilable and semantically similar. We attack mainstream code summarization models with a large-scale available Java dataset to evaluate the effectiveness and efficiency of our approach. The experimental results indicate that CREATE’s attack effectiveness and efficiency surpasses other baselines, causing a decrease in the quality of generated comments by at least 40%. Furthermore, we investigate the magnitude of perturbation caused by CREATE during adversarial attacks, and the results show that the similarity between the adversarial samples generated by CREATE and the input code is approximately 0.8, demonstrating that it induces more minor perturbations compared to other baselines. Finally, we utilize CREATE for adversarial training of the model. Through experimentation, this approach indeed effectively enhances the model’s robustness.

Abstract Anomaly detection on attributed graphs is a crucial topic for practical applications. Existing methods suffer from semantic mixture and imbalance issue because they commonly optimize the model based on the loss function for anomaly discrimination, mainly focusing on anomaly discrimination and ignoring representation learning. Graph Neural networks based techniques usually tend to map adjacent nodes into close semantic space. However, anomalous nodes commonly connect with numerous normal nodes directly, conflicting with the assortativity assumption. Additionally, there are far fewer anomalous nodes than normal nodes, leading to the imbalance problem. To address these challenges, a unique algorithm, decoupled self-supervised learning for anomaly detection (DSLAD), is proposed in this paper. DSLAD is a self-supervised method with anomaly discrimination and representation learning decoupled for anomaly detection. DSLAD employs bilinear pooling and masked autoencoder as the anomaly discriminators. By decoupling anomaly discrimination and representation learning, a balanced feature space is constructed, in which nodes are more semantically discriminative, as well as imbalance issue can be resolved. Experiments conducted on various six benchmark datasets reveal the effectiveness of DSLAD.

With the fast development of large software projects, automatic code summarization techniques, which summarize the main functionalities of a piece of code using natural languages as comments, play essential roles in helping developers understand and maintain large software projects. Many research efforts have been devoted to building automatic code summarization approaches. Typical code summarization approaches are based on deep learning models. They transform the task into a sequence-to-sequence task, which inputs source code and outputs summarizations in natural languages. All code summarization models impose different input size limits, such as 50 to 10,000, for the input source code. However, how the input size limit affects the performance of code summarization models still remains under-explored. In this article, we first conduct an empirical study to investigate the impacts of different input size limits on the quality of generated code comments. To our surprise, experiments on multiple models and datasets reveal that setting a low input size limit, such as 20, does not necessarily reduce the quality of generated comments. Based on this finding, we further propose to use function signatures instead of full source code to summarize the main functionalities first and then input the function signatures into code summarization models. Experiments and statistical results show that inputs with signatures are, on average, more than 2 percentage points better than inputs without signatures and thus demonstrate the effectiveness of involving function signatures in code summarization. We also invite programmers to do a questionnaire to evaluate the quality of code summaries generated by two inputs with different truncation levels. The results show that function signatures generate, on average, 9.2% more high-quality comments than full code.

Cryptocurrency phishing scams is a significant treat to Ethereum, one of the most popular blockchain platforms. Most of existing Ethereum phishing detection methods are based on traditional machine learning or graph representation learning, which mostly rely on only statistical and structural features in local scope. In this paper, we propose Multi-transaction-view Graph Attention Network (MTvGAT), a novel phishing scam detection model that can make use of transaction patterns of different scopes. To obtain global-view information, we apply graph clustering and construct the global-view graph with multiple clusters, including all the nodes of the original transaction network. To obtain local view information, we apply neighborhood sampling, and construct local-view graphs with target nodes and their neighborhood nodes. Then, node features, edge features, and attention coefficients are aggregated to merge multi-view information into representation of nodes. We further combine global-view and local-view representations to finally identify phishing addresses from target nodes. Extensive experiments demonstrate that the proposed method can outperform existing ones with significant improvement.

Byzantine Fault Tolerant (BFT) state machine replication protocols are used to achieve agreement among replicated servers with arbitrary faults. Most existing BFT protocols perform well in fault-free cases, but usually suffer from serious performance degradation when faults occur. In this paper, we present DBFT, a BFT protocol that realizes graceful performance degradation in faulty cases. The major novelty of DBFT lies in the double-response mechanism, which lets replica nodes deterministically respond to clients twice: one is after the speculative execution phase and the other is after the commitment phase. The double-response mechanism ensures good performance in spite of inconsistency in speculative execution. Also, to further alleviates undetectable performance attacks by a smartly malicious primary, we change primary upon every outstanding request. Moreover, DBFT does not involve clients in critical consensus operations so as to reduce the load of clients. We prove the correctness properties, i.e., safety and liveness, of DBFT. We conduct extensive experiments and the results show that, DBFT outperforms similar BFT protocols obviously in normal cases.

Applications on blockchain are currently limited by the relatively poor performance of the blockchain network such as low TPS, high latency and the resulting high transaction fees. Hence, performance optimization is one crucial problem of blockchain. Focusing on the most prosperous public blockchain Ethereum, we model the on-chain transaction confirmation process with the knowledge of Poisson process and queueing theory, derives the mean transaction-confirmation time, and explores the effect of different transaction fees on latency. We also conduct a numeric simulation of the model, which indicates that the model fits in well with the real world blockchain.

In this paper, we propose a novel two-dimensional frequency and time diversity aided orthogonal frequency division multiplexing based differential chaos shift keying (OFDM-DCSK) system. Our aim is to provide secure and robust transmissions for practical wireless systems, where perfect channel state information (CSI) may not be available at the receiver, by exploiting the natural high security of chaotic sequences and frequency diversity gains brought by the frequency hopping (FH). In our design, the information bits are firstly modulated by chaotic chips, then non-repetitive FH operations are performed on both reference chips and chaotic modulated symbols. After the inverse fast Fourier transform (IFFT), the non-repetitive reference chips and chaotic modulated symbols are respectively transmitted over different subcarriers. Subsequently, the receiver recovers the information using the received reference chaotic chips which naturally embed the channel frequency response (CFR) of all subcarriers. We then analyze the energy and spectral efficiencies, derive the bit error rate (BER) and information leakage expressions, and provide a detailed complexity analysis of the proposed scheme. Simulation results verify the effectiveness of our derivations and demonstrate that the proposed system achieves better BER and security performances compared with the benchmark system, especially when the CSI is imperfect or unknown.

The surging interest in blockchain has revitalized the search for efficient Byzantine fault-tolerant (BFT) protocols, which are used for blockchains to achieve consensus among replicated data blocks. Most existing BFT protocols perform well in fault-free cases, but they usually suffer from serious performance degradation when faults occur. In this paper, we present DBFT, a BFT protocol that realizes graceful performance degradation in normal cases. The major novelty of DBFT lies in the double-response mechanism, which lets replica nodes deterministically respond to clients twice: one is after the speculative execution phase and the other is after the commitment phase. The double-response mechanism can handle inconsistency in speculative execution, so as to alleviate performance degradation caused by faults. Moreover, DBFT does not involve clients in critical consensus operations so as to reduce the load of clients. The correctness properties, i.e., safety and liveness, of DBFT is rigorously proved. The performance of DBFT is evaluated via experiments and the results show that, DBFT outperforms similar BFT protocols obviously in normal cases.

In this paper, we study the power allocation and cluster scheduling in a downlink non-orthogonal multiple access (NOMA) network deployed with massive internet of things (IoT) devices with constraints of battery capacity. Our objective is to minimize the total transmit power while meeting the quality of service (QoS) demands for each IoT device. In the considered NOMA network, each cluster can multiplex the access of more than two IoT devices. We derive the minimum power allocated to every IoT device in each cluster with considerations of the QoS demands. Then we use the potential game model to characterize this NOMA network, and present a cluster scheduling scheme. Simulation results demonstrate that using the proposed algorithm, the consumed power is far less than the power consumed by the conventional orthogonal multiple access (OMA) scheme and the conventional NOMA scheme.

In this paper, we proposed a novel carrier interferometry (CI) code index modulation aided orthogonal frequency division multiplex (OFDM) differential chaotic shift keying (DCSK) communication system. In our design, we utilize the orthogonality property of CI codes matrix, and propose to transmit more information bits using the index of the CI codes matrix. The input information stream is divided into two subsets. One subset is modulated by the chaotic sequence and then spread by the information-bearing CI codes matrix which carries another information subset. At the receiver, the non-coherent chaotic demodulation and the maximum likelihood detection are respectively performed on these two subsets to retrieve the information. Since more bits can be transmitted while not requiring extra chaotic sequences and remaining the same overall energy, the energy efficiency is improved. Additionally, thanks to the spreading in the frequency domain achieved by the usage of CI codes, the peak to average power ratio (PAPR) can be suppressed. Moreover, theoretical performances including the energy efficiency, the bit error rate (BER) expressions are analyzed. Simulation results are provided to validate the theoretical analysis, and demonstrate the satisfactory PAPR and BER performances achieved by our design.

Light fidelity (LiFi) provides a promising solution for indoor high-speed wireless transmissions. However, the dense deployment of access points (APs) and the unity frequency reuse in LiFi system may induce the inter-cell interference (ICI) issue. In this paper, we consider the combined transmission (CT) which converts harmful interference to useful signals and thereby combats the ICI, and propose a dynamic user-centric clustering scheme for the downlink LiFi system. In our design, with the objective of maximizing the system throughput under proportional fairness constraints, the CT clustering is formulated as a mixed-integer non- linear programming (MINLP) problem. Then we set up an exact potential game (EPG) model, where the Nash equilibrium is found via the best response algorithm, to provide a suboptimal solution to the MINLP problem. Simulation results demonstrate that the LiFi system using our presented scheme exhibits a higher throughput and a better satisfaction degree than that employing the single-point transmission (SPT) scheme.