Knowledge graphs (KGs) serve as a vital backbone for a wide range of AI applications, including natural language understanding and recommendation. A promising yet underexplored direction is numerical reasoning over KGs, which involves inferring new facts by leveraging not only symbolic triples but also numerical attribute values (e.g., length, weight). However, existing methods fall short in two key aspects: (1) Incomplete semantic integration: Most models struggle to jointly encode entities, relations, and numerical attributes in a unified representation space, limiting their ability to extract relation-aware semantics from numeric information. (2) Ordinal indistinguishability: Due to subtle differences between close values and sampling imbalance, models often fail to capture fine-grained ordinal relationships (e.g., longer, heavier), especially in the presence of hard negatives. To address these challenges, we propose NumCoKE—a numerical reasoning framework for KGs based on Mixture-of-Experts and Ordinal Contrastive Embedding. To overcome (C1), we introduce a Mixture-of-Experts Knowledge-Aware (MoEKA) encoder that jointly aligns symbolic and numeric components into a shared semantic space, while dynamically routing attribute features to relation-specific experts. To handle (C2), we propose Ordinal Knowledge Contrastive Learning (OKCL), which constructs ordinal-aware positive and negative samples using prior knowledge, enabling the model to better discriminate subtle semantic shifts. Extensive experiments on three public KG benchmarks demonstrate that NumCoKE consistently outperforms competitive baselines across diverse attribute distributions, validating its superiority in both semantic integration and ordinal reasoning.

As cyberattacks on valuable digital assets increase in frequency and sophistication, traditional security gateways are becoming more vulnerable due to their reliance on complex software environments with unpatched vulnerabilities. To address this, we propose a hybrid security gateway that integrates FPGA-based hardware protection to filter out illegitimate traffic and shield the system from external attacks. Our architecture incorporates a novel security protocol based on the Noise Protocol Framework and modern cryptographic algorithms. By modularizing core encryption and filtering tasks and offloading them to independent FPGA components, we reduce the attack surface and enhance overall security. We implemented a prototype and conducted extensive security and usability tests, showing that our system matches the network throughput of traditional gateways while significantly improving resistance to cyber threats, without adding excessive latency.

In the face of rising dangers to the internal network due to remote cooperation, VPN gateways are an important tool for organisational network administrators, and the appropriate execution of VPN gateway functions is a vital component in safeguarding the internal network. The VPN gateway confronts security risks from the underlying cryptographic algorithm library, the current operating system, and the central processor as the number of attackers grows and attack methods evolve. In this paper, we propose a pure hardware logic VPN gateway to address security threats from the cryptographic algorithm library, operating system, and CPU by independently implementing the WireGuard protocol’s underlying cryptographic algorithm and building the WireGuard protocol’s hardware logic circuit on the FPGA platform. Actual testing on the NetFPGA-1G-CML platform reveals that the system’s network throughput can reach 35Mbps/s, whereas the network throughput of the software’s WireGuard VPN is 23Mbps/s under the same network settings. Simultaneously, the delay statistics of 300 repetitions of data packet encryption were performed. The encryption latency was less than 20 microseconds when the data packet size was the default MTU.098

Since gait is hard to imitate and can be easily collected by smartphone inertial sensors, it can be applied to user authentication. Traditional neural network based methods tend to train feature extractor and classifier together for each user in user authentication. These methods are difficult to guarantee that the feature extractor designed for specific users is suitable for other users. The accuracy is low when the sample size of a legitimate user is small, and the time overhead is heavy when the total amount of legitimate users is large. Besides, there are often strong constraints on sensor position, walking route, walking speed and external scenario when collecting gait data. In this paper, in order to reduce the cost of time and improve the robustness of the model, we use the idea of transfer learning to design our Gait2Vec feature extractor. It is pre-trained in the user identification task and then transferred to user authentication task for feature extraction. Meanwhile, a gait dataset of 21 subjects is collected under weak constraints in 2 scenarios for experimental purposes. Extensive analysis demonstrates that our models achieve a high performance with the accuracy over 94% in user identification and 97% in user authentication.

Zero shot learning aims to recognize objects whose instances may not be covered by the training data. To generalize knowledge from seen classes to the novel ones, semantic space is built to embed knowledge from various views into multi-modal semantic embeddings. Existing semantic embeddings neglect the relationships between classes which are essential to transfer knowledge between classes. Moreover, existing zero shot learning models ignore the complementarity between semantic embeddings from different modalities. To tackle these problems, in this work, we resort to graph theory to explicitly model the interdependence between classes and then obtain new modal semantic embeddings. Furthermore, we pioneer to propose a multi-level fusion model to effectively combine knowledge encoded in multi-modal semantic embeddings together. By the virtue of subsequent fusion block, the results of multi-level fusion can be furtherly enriched and fused. Experiments show that our model could achieve promising results on various datasets. Ablation study suggests that our method is well suited for zero shot learning.

Traditional recommendation methods aim to recom-mend personalized items by analyzing user's history interaction data. They ignore the fact that the data follows a long-tail distribution, which means that a small number of popular items account for most of the interaction records. This phenomenon causes the model to recommend more popular items, resulting in a severe popularity bias. In order to pay more attention to the long-tail items and debias the popular bias, we propose a Bilateral-Branch Graph Neural Network(BiGNN). In the long- tail branch, we construct a separate long-tail sub graph by eliminating the popular items with high degree. When the Graph Neural Network(GNN) aggregates information layer by layer in the subgraph, the receptive field of the single hop becomes larger, which increases the exposure of the long-tail items. Besides, another branch takes the original interaction graph as input to learn the general data distribution and generate the global embeddings of users and items. The two branches use the same GNN structure and share parameters. We employ the point-wise mutual information (PMI) strategy to indicate interaction between users and reconstruct the long-tail sub graph. The two branches are aggregated through an accumulated learning module, which makes the model first learn the conventional patterns and then pay attention to the long-tail data gradually. Extensive experiments on three real-world datasets show that BiGNN evidently outperforms the state-of- the-art methods consistently.

More and more work has focused on incorporating different kinds of literals into Knowledge Graph to promote the performance of knowledge embedding. These literals contain numeric literals, text literals, image literals and so on. These additional descriptions are connected to the entities through certain attributes. To incorporate numeric literals, some methods combine the embeddings of literals part with the traditional part - embeddings of entities. However, in the construction of literals embeddings, these existing methods consider the differences of these attributes: one dimension represents one attribute. But they ignore semantic meanings of attributes themselves. In this paper, we propose two methods to incorporate attributes semantics into knowledge graph embeddings from two perspectives: LiteralEAN and literalE-AT. They concatenate with the embeddings of numeric literals by different ways. Furthermore, their extension model LiteralE-C is also proposed as having a more comprehensive representation of attributes semantics. In an empirical study over two standard datasets FB15k and FB15k-237, we evaluate our models for link prediction. We demonstrate that they show an effective way to improve LiteralE and achieve state-of-the-art results. In ablation experiments, we find combined models do better than their singular counterparts in most cases.

The blooming of live comment videos leads to the need of automatic live video comment generating task. Previous works focus on autoregressive live video comments generation and can only generate comments by giving the first word of the target comment. However, in some scenes, users need to generate comments by their given prompt keywords, which can't be solved by the traditional live video comment generation methods. In this paper, we propose a Transformer based non-autoregressive conditional masked live video comments generation model called CMVCG model. Our model considers not only the visual and textual context of the comments, but also time and color information. To predict the position of the given prompt keywords, we also introduce a keywords position predicting module. By leveraging the conditional masked language model, our model achieves non-autoregressive live video comment generation. Furthermore, we collect and introduce a large-scale real-world live video comment dataset called Bili-22 dataset. We evaluate our model in two live comment datasets and the experiment results present that our model outperforms the state-of-the-art models in most of the metrics.

Knowing exact demographic attributes of users is crucial for human-computer interaction, intelligent marketing and automatic advertising. Ubiquitous sensor devices yield massive volumes of temporal data which hide a lot of valuable demographic information. In this paper, we bridge the gap between sensor data and demographic prediction to obtain real attributes of users from popular sensor devices: pedometer, which is widely used in mobile devices. We propose a novel model named Separated Embedding and Correlation Learning (SECL) for demographic prediction. Specifically, SECL first process the input data with a separated embedding layer to disentangle task-specific features for interference eliminating, and then capture the hidden correlations between different tasks via a correlation learning layer, finally the refined task-specific features are fed into a multi-task prediction layer to predict demographic attributes. Experimental results show impressive performance of our model on a real-world pedometer dataset, which is made publicly available on https://github.com/deepdeed/SECL.

ARM series processors are increasingly used in IoT and cloud services because of their high performance and flexibility of hardware design, especially Cortex-A9 MPCore processor. However, they also suffer from various types of security threats, typically such as flush-based cache attacks. Among these attacks, flush-based Spectre attacks(using Flush + Reload for Spectre attacks) represent a serious threat to system. They usually induce the victim to speculatively perform operations that would not occur during the correct program execution, and then leak the victim’s confidential information to the adversary via cache side channel attacks. So far, there is no widely accepted solution to defend against Spectre attacks. The proposed solutions either lead to large performance losses or sacrifice transparency. In this paper, we propose a secure flush operation API named Flush-Detector to mitigate flush-based Spectre attacks. We present the design and implement of Flush-Detector to detect and defend against flush-based Spectre attacks on ARM Cortex-A9 MPCore. The attack experimental results show that Flush-Detector can detect flush-based Spectre attacks in real time and reduce the attack success rate to less than 1%. Moreover, performance test results demonstrate that the time consumption of Flush-Detector API is about 17.7% longer than the original cache flush API.

The SM4 algorithm is the first commercial cryptographic algorithm officially announced in China for wireless local area network products. It is suitable for scenarios that require high real-time performance, such as wireless communication and IoT sensor nodes. It can be seen that the security research of the SM4 algorithm is of great significance to wireless devices in the IoT. Like other symmetric encryption algorithms, the SM4 algorithm faces some security threats, such as side-channel attacks. Among them, cache timing attacks and power/electromagnetic analysis attacks are becoming more and more threatening due to their low execution difficulty and powerful attack capabilities. Most implementations of anti-side channel attacks against the SM4 algorithm can only resist one of above two attacks. However, side-channel leakages associated with above attacks often coexist.Therefore in this paper, we present a hardware/software collaborative SM4 implementation on ARM-FPGA embedded SoC which can resist above two types of attacks simultaneously. It randomly divides the 32 rounds of SM4 encryption into three stages: the beginning software stage, the middle hardware stage, and the final software stage. Besides, we shuffle the order of some independent operations in each round of the software stages and add dummy rounds to the hardware stage. Finally, we conduct above two types of attacks on unprotected software/hardware SM4, shuffled software SM4 and our scheme, then evaluate their performance respectively. The data throughput of our scheme is 0.86 times that of the original software SM4, while the FPGA resource requirements of our scheme are 0.87 times that of the unprotected hardware implementation.

Since the master key length becomes longer and longer in ciphers, an adversary often needs to preform the multi-round side channel analysis (SCA) in order to recover the master key by enough round keys. Traditional multi-round SCA is launched by adaptive manner in practice, which means that the input of each round is calculated in an on-the-fly way based on all round keys of anterior rounds. However, compared to the classical single-round SCA, the multi-round SCA in adaptive manner is severely limited in several practical scenarios, because all round keys of anterior rounds must be properly recovered before the attack against the next round. In this paper, we focus on the Feistel-SP networks, break the interdependency between the alternating measurement and analysis phases, propose a Multi-round non-Adaptive Chosen Message (MACM) approach, which can reduce the multi-round SCA to the single-round attack. In MACM, the set of plaintexts applied to multiple rounds is calculated in an off-line way. We also prove that the revealed round keys by MACM are adequate to recover the master key. Furthermore, we carefully analyze the advantages of MACM regarding to robustness and compatibility. In order to further manifest the validity of MACM, we perform extensive experiments on three typical Feistel-SP ciphers, Camellia, CLEFIA and SM4, the master keys are recovered as expected, and the number of traces in MACM is at least 25% less than that in the adaptive manner.

With the popularity of smart devices such as mobile phones and tablets, the security problem of the widely used ARMv8-A processor has received more and more attention. Flush+Reload and Flush+Flush cache attacks have become two of the most important security threats due to their low noise and high resolution. In order to resist Flush+Reload and Flush+Flush attacks, researchers proposed many defense methods. However, these existing methods have various shortcomings. The runtime defense methods using hardware performance counters cannot detect attacks fast enough, effectively detect Flush+Flush or avoid a high false positive rate. Static code analysis schemes are powerless for obfuscation techniques. The approaches of permanently reducing the resolution can only be utilized on browser products and cannot be applied in the system. In this paper, we design two more secure collaborative APIs-flush operation API and high resolution time API-which can resist Flush+Reload and Flush+Flush attacks. When the flush operation API is called, the high resolution time API temporarily reduces its resolution and automatically restores. Moreover, the flush operation API also has the ability to detect and handle suspected Flush+Reload and Flush+Flush attacks. The attack and performance comparison experiments prove that the two APIs we designed are safer and the performance losses are acceptable.

ARM-FPGA embedded SoCs have been widely used in the fields of drones, embedded and IoT devices due to its high performance and hardware design flexibility. However, ARM-FPGA embedded SoC suffers various types of security threats, one of which is flush-based cache attack. The proposed defense schemes either lead to a high false positive rate or a large performance loss. Due to the importance of high resolution time APIs in the system, schemes that permanently reduce the resolution of time APIs can only be implemented in specific applications such as browsers. Moreover, the method of protecting high resolution timers in software cannot defend against an attacker with root privileges. In this paper, we propose a more secure timer which is a hardware/software co-design on ARM-FPGA embedded SoC. When a software process calls the flush operation, the timer adaptively reduces its resolution and recover after a short period of time. In the case that the flush operation is not called, the impact of the timer on system performance is almost negligible. This hardware/software co-design guarantees the availability of a high resolution time API while defend against attackers with root privileges. The results of the attack experiments show that the success rates of Flush+Reload and flush-based Spectre attacks can be reduced to less than 1% when using the timer. Performance test results show that the timer access latency is 9.5% slower than the fastest PMCCNTR but 5% faster than the global timer of Cortex-A9 MPCore. The modified flush operation API for the design only increases the time consumption by about 12%.

Detecting local topic from social media is an important task for many applications, such as local event discovery and activity recommendation. Recent years have witnessed growing interest in utilizing spatio-temporal social media for local topic detection. However, conventional topic models consider keywords as independent items, which suffer great limitations in modeling short texts from social media. Therefore, some studies introduce embedding into topic models to preserve the semantic correlation among keywords of short texts. Nevertheless, due to the lack of rich contexts in social media, the performance of these embedding based topic models still remain unsatisfactory. In order to enrich the contexts of keywords, we propose two network based embedding methods, both of which can generate rich contexts for keywords by random walks and produce coherent keyword embeddings for topic modeling. Besides, processing continuous spatio-temporal information in social media is also very challenging. Most of the existing methods simply split time and location into equal-size units, which fall short in capturing the continuity of spatio-temporal information. To address this issue, we present a hotspot detection algorithm to identify spatial and temporal hotspots, which can address spatio-temporal continuity and alleviate data sparsity. Finally, the experiments show that the performance of our methods has been improved significantly compared to the state-of-the-art methods.

Low-entropy masking schemes and shuffling technique are two common countermeasures against traditional side-channel analysis. Improved Rotating S-box Masking (RSM) is a combination of both countermeasures and is implemented by DPA contest committee to improve the software security level of AES-128. Compared with the original version, improved RSM mainly introduces both the offset and shuffle array as security foundations to counteract the existing attacks. In this paper, we first point out a general vulnerability referred to as "leakage fingerprints" and make use of it to successfully crack the offset array with 100% accuracy, which breaks down the masking countermeasure in the first step. Then, we show that cracking the shuffle array is still feasible but not necessary since several other vulnerabilities in the implementation level can be exploited to bypass the shuffle countermeasure directly. By selectively combining all these vulnerabilities, a dozen of attacks can be put forward, and we perform two of them as examples to verify their effectiveness. Official evaluation results show that, both attacks submitted by us are practical and feasible, and also operate with high efficiency. In terms of two major performance metrics, our best scheme requires 4 traces to reveal the AES master key with 80% Global Success Rate (GSR) and only 2 traces are enough to reduce the Maximum Partial Guessing Entropy (PGE) under 10.