Protein-protein Interaction (PPI) prediction, which aims to identify the interactions between proteins within a biological system, is an important problem in understanding disease mechanisms and drug discovery. Recently, Equivariant Graph Neural Networks (E3-GNNs) are advanced computational models that provide a powerful solution for accurately predicting PPIs by preserving the geometric integrity of protein interactions. However, most E3-GNNs model protein interactions at the residue level, potentially neglecting critical atomic details and side-chain conformations. In this paper, we propose a novel model, MEANT, designed to adaptively extract atom-level geometric information from varying numbers of atoms within different residues for PPI prediction. Specifically, we define a full-atom graph that contains atomic geometry and guides the message passing under the structure of residues. We also design a geometric relation extractor to integrate geometric information from different residues and adaptively handle variations in the number of atoms within each residue. Finally, we adopt the attention mechanism to update the residue representation and the atomic coordinates within a residue. Experimental results show that our proposed model, MEANT, significantly outperforms state-of-the-art methods on three typical PPI prediction tasks. Our code and data are available on GitHub at https://github.com/BUPT-GAMMA/MEANT.

Trajectory data is crucial for various applications but often suffers from incompleteness due to device limitations and diverse collection scenarios. Existing imputation methods rely on sparse trajectory or travel information, such as velocity, to infer missing points. However, these approaches assume that sparse trajectories retain essential behavioral patterns, which place significant demands on data acquisition and overlook the potential of large-scale human trajectory embeddings. To address this, we propose ProDiff, a trajectory imputation framework that uses only two endpoints as minimal information. It integrates prototype learning to embed human movement patterns and a denoising diffusion probabilistic model for robust spatiotemporal reconstruction. Joint training with a tailored loss function ensures effective imputation. ProDiff outperforms state-of-the-art methods, improving accuracy by 6.28\% on FourSquare and 2.52\% on WuXi. Further analysis shows a 0.927 correlation between generated and real trajectories, demonstrating the effectiveness of our approach.

Continual Relation Extraction (CRE) has found widespread web applications (e.g., search engines) in recent times. One significant challenge in this task is the phenomenon of catastrophic forgetting, where models tend to forget earlier information. Existing approaches in this field predominantly rely on memory-based methods to alleviate catastrophic forgetting, which overlooks the inherent challenge posed by the varying memory requirements of different relations and the need for a suitable memory refreshing strategy. Drawing inspiration from the mechanisms of Dynamic Random Access Memory (DRAM), our study introduces a novel CRE architecture with an asynchronous refreshing strategy to tackle these challenges. We first design a DRAM-like architecture, comprising three key modules: perceptron, controller, and refresher. This architecture dynamically allocates memory, enabling the consolidation of well-remembered relations while allocating additional memory for revisiting poorly learned relations. Furthermore, we propose a compromising asynchronous refreshing strategy to find the pivot between over-memorization and overfitting, which focuses on the current learning task and mixed-memory data asynchronously. Additionally, we explain the existing refreshing strategies in CRE from the DRAM perspective. Our proposed method has experimented on two benchmarks and overall outperforms ConPL (the SOTA method) by an average of 1.50% on accuracy, which demonstrates the efficiency of the proposed architecture and refreshing strategy.

The heterogeneous information network (HIN), which contains rich semantics depicted by meta-paths, has emerged as a potent tool for mitigating data sparsity in recommender systems. Existing HIN-based recommender systems operate under the assumption of centralized storage and model training. However, real-world data is often distributed due to privacy concerns, leading to the semantic broken issue within HINs and consequent failures in centralized HIN-based recommendations. In this paper, we suggest the HIN is partitioned into private HINs stored on the client side and shared HINs on the server. Following this setting, we propose a federated heterogeneous graph neural network (FedHGNN) based framework, which facilitates collaborative training of a recommendation model using distributed HINs while protecting user privacy. Specifically, we first formalize the privacy definition for HIN-based federated recommendation (FedRec) in the light of differential privacy, with the goal of protecting user-item interactions within private HIN as well as users' high-order patterns from shared HINs. To recover the broken meta-path based semantics and ensure proposed privacy measures, we elaborately design a semantic-preserving user interactions publishing method, which locally perturbs user's high-order patterns and related user-item interactions for publishing. Subsequently, we introduce an HGNN model for recommendation, which conducts node- and semantic-level aggregations to capture recovered semantics. Extensive experiments on four datasets demonstrate that our model outperforms existing methods by a substantial margin (up to 34% in HR@10 and 42% in NDCG@10) under a reasonable privacy budget (e.g., ε=1).

Abstract Text-to-image (TTI) models provide huge innovation ability for many industries, while the content security triggered by them has also attracted wide attention. Considerable research has focused on content security threats of large language models (LLMs), yet comprehensive studies on the content security of TTI models are notably scarce. This paper introduces a systematic tool, named EvilPromptFuzzer, designed to fuzz evil prompts in TTI models. For 15 kinds of fine-grained risks, EvilPromptFuzzer employs the strong knowledge-mining ability of LLMs to construct seed banks, in which the seeds cover various types of characters, interrelations, actions, objects, expressions, body parts, locations, surroundings, etc. Subsequently, these seeds are fed into the LLMs to build scene-diverse prompts, which can weaken the semantic sensitivity related to the fine-grained risks. Hence, the prompts can bypass the content audit mechanism of the TTI model, and ultimately help to generate images with inappropriate content. For the risks of violence, horrible, disgusting, animal cruelty, religious bias, political symbol, and extremism, the efficiency of EvilPromptFuzzer for generating inappropriate images based on DALL.E 3 are greater than 30%, namely, more than 30 generated images are malicious among 100 prompts. Specifically, the efficiency of horrible, disgusting, political symbols, and extremism up to 58%, 64%, 71%, and 50%, respectively. Additionally, we analyzed the vulnerability of existing popular content audit platforms, including Amazon, Google, Azure, and Baidu. Even the most effective Google SafeSearch cloud platform identifies only 33.85% of malicious images across three distinct categories.

Abstract Abnormal traffic detection is a crucial topic in the field of network security. However, existing methods face many challenges when processing complex high-dimensional traffic data. Especially in dealing with redundant features, data sparsity and nonlinear features, traditional methods often suffer from high computational complexity and low detection efficiency. It is challenging to capture potential patterns in complex data effectively and cannot fully meet the needs of practical applications. To address these challenges, this paper proposes an enhanced anomaly traffic detection framework using bidirectional generative adversarial networks (BiGAN) and contrastive learning. This method preprocesses high-dimensional data through steps such as data cleaning, normalization, and clustering to improve data quality. It uses BiGAN and contrastive learning technology to enhance the model's feature representation capabilities. Experimental results show that the method proposed in this paper performs well on multiple traffic data sets and significantly improves the accuracy and efficiency of anomaly detection. Overall, the solution proposed in this paper effectively overcomes the limitations of existing methods in high-dimensional data processing and provides a more advanced abnormal traffic detection strategy.

Abstract Network traffic anomaly detection is a critical issue in network security. Existing Abnormal traffic detection methods rely on statistical-based or anomaly-based approaches, and these detection methods all require a full understanding of traffic characteristics and attack patterns. Information entropy has been widely studied in abnormal traffic detection because it can describe the distribution characteristics of network traffic. However, this method makes it difficult to cope with the timing and variability of network traffic. To address these challenges, this paper proposes a network traffic anomaly detection method based on Renyi entropy. Simultaneously, we introduce a fixed time window and utilize an improved EWMA model within this window to dynamically set thresholds for anomaly detection. Experimental results show that the method proposed in this paper is superior to popular abnormal traffic detection methods in terms of effectiveness and efficiency, it is better adapted to the dynamic changes of network traffic and provides a more reliable solution for anomaly detection.

The fifth-generation mobile communication network (5G) is a significant infrastructure with the support of enhanced mobile broadband, ultra-reliable and low latency communication, and massive machine type communication. Due to the large-scale application of 5G in industrial control field, the security of 5G network has become an important issue. In order to efficiently perform security detection on 5G radio access network protocols, we propose an intelligent fuzzing algorithm for 5G NAS protocol based on predefined rules. Through the analysis of the 3GPP NAS protocol technical specification and captured packets, a message structure table is extracted based on the NAS message format and field properties. Different mutation strategies are then dynamically assigned to different key fields to realize the intelligence of the message mutation process. Furthermore, in order to evaluate the performance of the algorithm, we implement a fuzzing prototype system based on this intelligent mutation algorithm, and then conduct practical security detection on 5G NAS protocol in OAI, an open-source software radio simulation environment. Experimental results show that our proposed intelligent mutation algorithm has better performance in terms of protocol state coverage and the scale of test cases. In addition, five types of security vulnerabilities in OAI are also exposed in this paper, namely buffer overflow, use-after-free, infinite loop, memory access for uninitialized address, and memory access for NULL pointers. These vulnerabilities could result in denial of registration services to users.

Anomaly-based Web application firewalls (WAFs) are vital for providing early reactions to novel Web attacks. In recent years, various machine learning, deep learning, and transfer learning-based anomaly detection approaches have been developed to protect against Web attacks. Most of them directly treat the request URL as a general string that consists of letters and roughly use natural language processing (NLP) methods (i.e., Word2Vec and Doc2Vec) or domain knowledge to extract features. In this paper, we proposed an improved feature extraction approach which leveraged the advantage of the semantic structure of URLs. Semantic structure is an inherent interpretative property of the URL that identifies the function and vulnerability of each part in the URL. The evaluations on CSIC-2020 show that our feature extraction method has better performance than conventional feature extraction routine by more than average dramatic 5% improvement in accuracy, recall, and F1-score.

This paper proposes a network model that combines long and short feature extractors to solve the problem of automatic classification of web pages. By analyzing the current major portal websites, the main categories of original corpus are formulated. By analyzing the composition of webpage content, the composite extraction features of long and short feature extractors are designed. The attention mechanism is introduced in the short feature extraction network to enhance the ability of short text information extraction. For the longer text, the long feature extraction network combines the attention mechanism of the word and segment to capture information. In the last layer of the classification, the correction mechanism is used for model fusion, which further improves the accuracy of classification. The experimental results show that the proposed method has higher classification accuracy. The classification indicators under the first-level label all reached 0.94 or higher, and 0.90 under the secondary label. The composite feature extraction network designed in this paper has better anti-noise ability and classification efficiency, and can achieve higher classification accuracy.

In the data analysis processing based on the statistic data warehouse, we divided the hierarchy of Web-based Decision Support System Intelligent Agent into different layers, which were named method, model and application intelligent agent layer. This paper introduces the definition and function for each layer in Statistic data warehouse, also gives the theory and practice in it.