Ultrasonic injection attacks have emerged as a critical security threat to voice-controlled devices in the Internet of Things (IoT).However, most existing attack methods are limited to single-device, fixed-direction point-to-point attacks. For the first time, this paper presents a novel ultrasonic voice injection attack method—Phased Array Attack (PAA)—which enables flexible control of the attack direction. PAA expands the traditional point-to-point attack paradigm to a point-to-area approach, allowing any devices within a 45° sector to be attacked without physically moving the transmitting apparatus. This method significantly enhances the flexibility, scalability, and extensibility of injection attacks. PAA offers three key advantages: (1) high stealth: once deployed, it can target multiple devices; (2) high compatibility: the signal modulation process is offloaded from the hardware platform to a PC, thus avoiding limitations imposed by FPGA-based implementations and enabling the use of more powerful modulation algorithms; (3) theoretical soundness: PAA employs constructive interference and nonlinear demodulation theory to enhance attack performance. To validate the feasibility and effectiveness of the proposed approach, we developed an FPGA-based prototype attack system and systematically evaluated its performance in various application scenarios. Experimental results show that the proposed method achieves a high attack success rate at distances of up to 5 meters. These findings further highlight the severe physical-layer security challenges faced by voice-controlled devices in IoT environments.

Current state-of-the-art adversarial example detectors exhibit several fatal limitations, hindering their deployment in safety-critical real-world applications. These limitations include a lack of sufficient universality, vulnerability to adaptive attacks, high test-stage time consumption, and a lack of plug-and-play capability. To bridge the gap, this paper proposes a novel state-of-the-art adversarial example detector named Adversarial Detection on Purification (ADoP). Specifically, ADoP first incorporates a novel adversarial purification named Gaussian-augmented GAN-based Adversarial Purification (GA-GAP), which exhibits sufficient advantages. Then, ADoP effectively overcomes current limitations by fully exploiting the advantages of GA-GAP. Extensive experiments on ImageNet demonstrate ADoP’s effectiveness in universal detection, adaptive attack avoidance, reduced test-stage time, and plug-and-play capability.

The rapid advancement of Artificial Intelligence Generated Content (AIGC) technology has enabled deepfake videos to evolve from unimodal generation to audio-visual forgeries. Existing multimodal deepfake detection methods primarily rely on capturing correlations between audio-visual modalities to improve detection performance. However, in real-world scenarios, network jitter often leads to audio-visual asynchrony, disrupting inter-modal associations and limiting the effectiveness of these methods. To address this issue, we propose a deepfake detection method specifically designed for audio-visual asynchrony scenarios. First, based on the theory of open balls in metric space, we analyze the variation mechanism of joint features in both audio-visual synchrony and asynchrony scenarios, revealing the impact of audio-visual asynchrony on detection performance. Second, we design a multimodal subspace representation module to mitigate inconsistencies in feature distributions and representation heterogeneity between modalities. We then formulate audio-visual feature alignment as an integer linear programming task and employ the Hungarian algorithm to reconstruct missing inter-modal associations. Finally, we introduce a self-supervised masked reconstruction mechanism to reconstruct missing features and construct the joint correlation matrix to measure cross-modal dependencies, enhancing the robustness of detection. Extensive experiments demonstrate that our method outperforms baselines in audio-visual asynchrony scenarios and exhibits robustness against unknown disturbances.

Backdoor attacks have significantly threatened the models of natural language processing (NLP). However, most textual backdoor attacks exhibit low levels of stealthiness, making them susceptible to detection and removal by defense strategies. In order to improve the performance and stealthiness of such backdoor attacks, this article introduces a novel backdoor attack named Bad Padding (BPad) based on steganography. BPad employs a word‐substitution steganographic method to hide triggers in sentences, thereby generating poisoned data. To ensure a high level of stealthiness for these poisoned samples, BPad developed a word substitution strategy that enhances both the diversity of the substituted words and the contextual coherence of the sentences. BPad also modifies the preprocessing stage by extracting triggers from the sentences and padding them as tokens at the end, effectively amplifying the impact of the trigger and making it easier for the model to learn the shortcut from the trigger to the target label, thereby achieving the injection of a backdoor. This article uses various metrics to present experimental measures of the attack performance and stealthiness of BPad. The results find that BPad achieved competitive results compared to baseline methods in non‐defense scenarios and outperforms baseline methods under both training and inference defense. Besides that, the attack samples generated by BPad demonstrate strong stealthiness in terms of semantic coherence, perplexity, and grammaticality.

Transferable adversarial attacks against deep neural networks (DNNs) have attracted significant attention. Attackers can use adversarial examples crafted on substitute models to attack unknown target models, highlighting the importance of boosting transferability. However, the transferability of adversarial examples produced by current methods remains relatively weak. In this paper, we first propose an iterative attack based on frequency subspectrum mixup input transformation (FSMA), considering the sensitivity difference of model decision to different frequency components. Specifically, we evenly divide the discrete cosine transform spectra of noisy original image and auxiliary image into four disjoint subspectra respectively, and perform a mixup on each pair of subspectra to obtain diversified inputs to stabilize the perturbation update direction. Secondly, given the different noise phenomena in gradients of normally trained models and defenses, and the resulting gradient structure ambiguity, a structure-enhanced gradient purification strategy (SEGP) is proposed. By narrowing the difference between normal gradient and defense gradient, the success rate of adversarial examples in evading defenses is improved. We use convolutional neural network (CNN) and Transformer-based image classifiers as substitute models to craft adversarial examples. Plentiful experiments on ImageNet-compatible dataset prove the effectiveness of the proposed FSMA and SEGP. The latter can be combined with other attacks involving multi-sample average gradient processes to improve their success rate in breaking defenses. We also conduct a quantitative analysis of subspectrum mixup, illustrating the effectiveness of performing mixup on all subspectra. Our code is available at https://github.com/Rhiannon-lucky/FSMA .

Current state-of-the-art plug-and-play countermeasures for mitigating adversarial examples (i.e., purification and detection) exhibit several fatal limitations, impeding their deployment in safety-critical real-world applications. These limitations include susceptibility to adaptive attacks, adverse impact on benign samples, high time consumption for conducting a complete defense cycle, etc. To bridge the gap, developing more advanced plug-and-play countermeasures is urgently needed to safeguard these applications. Specifically, this paper first proposes a novel method named Gaussian-augmented GAN-based Adversarial Purification (GA-GAP). Unlike previous methods, GA-GAP enhances the density of the training data in low-robustness regions by using random Gaussian noise. Moreover, GA-GAP incorporates a pre-trained deep learning classifier into the training architecture and integrates its classification loss into the training loss function. Then, following the development of GA-GAP, this paper innovatively proposes a dual-function defense framework named Adversarial Detection on Purification (ADoP) to mitigate adversarial examples further. In ADoP, purification and detection complement each other, achieving the effect of$\mathbf {1+1\gt 2}$, which can more efficiently avoid adaptive attacks. Extensive experiments on ImageNet demonstrate that ADoP outperforms other countermeasures in multiple aspects. These aspects include superior generalization capability in purifying and detecting various adversarial examples, less adverse impact on benign samples, and practical time consumption for conducting a complete defense cycle.

Contrastive learning has received significant attention for its ability to improve the representation quality over limited labeled data, achieving notable advancements in Knowledge graphs (KGs) enhanced recommendation. However, the effectiveness of most contrastive methods heavily relies on manually designed data augmentation strategies, which often limit their generality across different datasets and downstream tasks, as well as their robustness to noise perturbations. To address these challenges, we propose a novel KG-enhanced recommendation framework namedKnowledgeGraph-enhancedMaskedAuto-Encoders forCollaborative Filtering (KG-CMAE) based on the masking-reconstruction paradigm, which employs two types of masked auto-encoders: the Knowledge Masked Auto-Encoder (KMAE) and the Collaborative Masked Auto-Encoder (CMAE), to adaptively extract informative self-supervised signals from KGs and user-item interactions. Specifically, KMAE employs the multi-head cross-attention mechanism to reflect the importance of neighboring nodes, and selectively masks and reconstructs the important connections with high structural consistency, thereby highlighting task-relevant knowledge. CMAE focuses on masking and reconstructing the interactions with high semantic relevance in the user-item interaction graph, and incorporates an enhanced decoder to better model the direct collaborative signals, such as user-user and item-item correlations, to mitigate the over-smoothing problem. Extensive experiments are conducted on three benchmark datasets under various settings, including noisy data, cold-start user recommendation, and long-tail item recommendation. The experimental results demonstrate the effectiveness, generality and robustness of the proposed KG-CMAE model compared to various baseline methods.

The existence of adversarial image makes us have to doubt the credibility of artificial intelligence system. Attackers can use carefully processed adversarial images to carry out a variety of attacks. Inspired by the theory of image compressed sensing, this paper proposes a new black-box attack, \(\mathcal {N}\text{-HSA}_{LF}\) . It uses covariance matrix adaptive evolution strategy (CMA-ES) to learn the distribution of adversarial perturbation in low frequency domain, reducing the dimensionality of solution space. And sep-CMA-ES is used to set the covariance matrix as a diagonal matrix, which further reduces the dimensions that need to be updated for the covariance matrix of multivariate Gaussian distribution learned in attacks, thereby reducing the computational cost of attack. And on this basis, we propose history-driven mean update and current optimal solution-guided improvement strategies to avoid the evolution of distribution to a worse direction. The experimental results show that the proposed \(\mathcal {N}\text{-HSA}_{LF}\) can achieve a higher attack success rate with fewer queries on attacking both CNN-based and transformer-based target models under \(L_2\) -norm and \(L_\infty\) -norm constraints of perturbation. We also conduct an ablation study and the results show that the proposed improved strategies can effectively reduce the number of visits to the target model when making adversarial examples for hard examples. In addition, our attack is able to make the integrated defense strategy of GRIP-GAN and noise-embedded training ineffective to a certain extent.

Anonymous data exchange is in great demand in many situations, especially in remote control systems, in which a stable, secure, and secret data channel must be established between the controlling and controlled parties to distribute control commands and return data. In the previous work, we built a two‐level Virtual-Space anonymous communication scheme based on the Crowds System for performing secret data exchange in remote control systems. However, as an essential part of security and anonymity, participating nodes’ identity declaration and session key agreement phases were not well designed. In this paper, we redesign the identity agreement and declaration process and design an identity‐based Virtual-Space agreement method using the extended Chebyshev Chaotic Maps. In this approach, we transform the identity declaration process into a multilevel Virtual-Space agreement problem, where a series of security‐progressive Virtual-Space addresses are negotiated between the controller and the controlled nodes. The protocol can handle the case where there are multiple controllers in the system, and the negotiated Virtual-Space depends on the identity of the controller and the controlled node, so different controllers do not affect each other. The designed protocol is verified on Freenet, and we conclude this paper with a detailed security analysis of the method to prove that the method satisfies forward security.

Rumors can spread very rapidly through online social networks (OSNs), leading to huge negative impact on human society. Hence, there is an urgent need to develop models that can minimize the spread of rumors. In this article, we propose a novel framework to improve the cost and efficiency of rumor propagation control. First, to reduce the impact of rumor controlling mechanism on users’ normal activities, we introduce a soft dynamic quarantine strategy into rumor propagation control and develop a new propagation model named susceptible-infected-removed-quarantined ignorants-quarantined spreaders (SIRQU) to model and block the rumor propagation in the network. Second, to further improve the control efficiency, we propose an influential node selection algorithm based on discrete particle swarm optimization with an evolutionary search strategy, and the controlling mechanism is only applied on the most influential nodes. Finally, we conduct a series of simulations and experiments on several public datasets and the dataset collected from Sina Weibo to validate the proposed method, and the results show that the proposed method outperfoms the related baseline algorithms.

The increasing use of recommender systems as personalization recommendation services such as Amazon, TripAdvisor, and Yelp, has stressed the demand for secure and usable abnormality detection techniques, due to fundamental vulnerabilities of recommender systems and their openness. With the emergence of new attacks, how to defend diverse malicious attacks for online recommendations is a challenging issue. Moreover, characterizing and evaluating sparse rating behaviors are a long-standing problem that still remains open, leading to an upsurge of research, as well as real application. This article investigates probabilistic inference and trustworthiness evaluation of behavioral links according to coupled association networks converted from rating behaviors, and presents a unified detection framework from a novel perspective to spot diverse malicious threats. First, an association graph is constructed from the original rating matrix based on both the inherent rating motivation of users and atomic propagation rules of coupled networks. Then, we evaluate the trustworthiness of link behaviors in the targeted network of coupled association network by exploiting a factor graph model of coupled network, and redetermine concerned links in the targeted network. Finally, suspicious users and items can be empirically inferred by comprehensively evaluating the trustworthiness of both links and nodes in the targeted network. Extensive experiments on synthetic data for profile injection attacks and co-visitation injection attacks, as well as real-world data including Amazon and TripAdvisor, demonstrate the effectiveness of the proposed detection approach compared with competing benchmarks.

Recommender system, as a data-driven way to help customers locate products that match their interests, is increasingly critical for providing competitive customer suggestions in many web services. However, recommender systems are highly vulnerable to malicious injection attacks due to their fundamental vulnerabilities and openness. With the endless emergence of new attacks, how to provide a feasible way for defending different malicious threats against online recommendations is still an under-explored issue. In this paper, we explore a new way to defend malicious injection attacks through user intention understanding and influential neighbour disclosure. Specifically, we propose a detection approach, termedTBOS(ThreeBirds withOneStone), to deal with different malicious threats. InTBOS, we first develop the discrimination of attack target by combining global influence evaluation and risk attitude estimation of users. In order to makeTBOScontrollable, second, we propose to incorporate an optimal denoising mechanism to remove disturbed information before detection. To enhance the representativeness and predictability of detection model, finally, we propose to leverage a behavioral label propagation mechanism based on constructed label space for the determination of malicious injection behaviors. Extensive experiments on both synthetic and real data demonstrate thatTBOSoutperforms all baselines in different cases. Particularly, the detection performance ofTBOScan achieve an improvement of 6.08% FAR (false alarm rate) for optimal-injection attacks, an improvement of 3.83% FAR in average for co-visitation injection attacks, as well as an improvement of 2.3% for profile injection attacks over benchmarks in terms of FAR while keeping the highest DR (detection rate). Additional experiments on real-world data show thatTBOSbrings an improvement with the advantage of 6.5% FAR in average compared with baselines.

Anonymous exchange of data has a strong demand in many scenarios. With the development of IoT and wireless networks, plenty of smart devices are interconnected through wireless technologies such as 5G and Wi-Fi, making it possible to use them for information exchanging. The authors find a P2P network model for secure and anonymous communication, which is a typical Crowds system and the operating mechanism meets the characteristics of limited-resources of IoT devices. Based on this network model, the authors design a lightweight communication scheme for the remote-control system in this work, using two kinds ofVirtual-Spaces to achieve the purpose of identity announced and data exchanged. The authors implemented a prototype system of the scheme and tested it over theFreenet, proving that the scheme can effectively resist the impact of flow analysis on the anonymity of communication while ensuring communication data security. By analyzing the scheme’s performance, the author believes that the scheme is practical and is suitable for scenarios that are not time-sensitive but require high anonymity.

Abstract Customer preferences analysis and modelling using deep learning in edge computing environment are critical to enhance customer relationship management that focus on a dynamically changing market place. Existing forecasting methods work well with often seen and linear demand patterns but become less accurate with intermittent demands in the catering industry. In this paper, we introduce a throughput deep learning model for both short-term and long-term demands forecasting aimed at allowing catering businesses to be highly efficient and avoid wastage. Moreover, detailed data collected from a business online booking system in the past three years have been used to train and verify the proposed model. Meanwhile, we carefully analyzed the seasonal conditions as well as past local or national events (event analysis) that could have had critical impact on the sales. The results are compared with the best performing forecast methods Xgboost and autoregressive moving average model (ARMA), and they suggest that the proposed method significantly improves demand forecasting accuracy (up to 80%) for dishes demand along with reduction in associated costs and labor allocation.

Personalized recommender systems are pervasive in different domains, ranging from e-commerce services, financial transaction systems to social networks. The generated ratings and reviews by users toward products are not only favourable to make targeted improvements on the products for online businesses, but also beneficial for other users to get a more insightful review of the products. In reality, recommender systems can also be deliberately manipulated by malicious users due to their fundamental vulnerabilities and openness. However, improving the detection performance for defending malicious threats including profile injection attacks and co-visitation injection attacks is constrained by the challenging issues: (1) various types of malicious attacks in real-world data coexist; (2) it is difficult to balance the commonality and speciality of rating behaviors in terms of accurate detection; and (3) rating behaviors between attackers and anchor users caused by the consistency of attack intentions are extremely similar. In this article, we develop a unified detection approach named IMIA-HCRF, to progressively discriminate malicious injection behaviors for recommender systems. First, disturbed data are empirically eliminated by implementing both the construction of association graph and enhancement of dense behaviors, which can be adapted to different attacks. Then, the smooth boundary of dense rating (or co-visitation) behaviors is further segmented using higher order potentials, which is finally leveraged to determine the concerned injection behaviors. Extensive experiments on both synthetic data and real-world data demonstrate that the proposed IMIA-HCRF outperforms all baselines on various metrics. The detection performance of IMIA-HCRF can achieve an improvement of 7.8% for mixed profile injection attacks as well as 6% for mixed co-visitation injection attacks over the baselines in terms of FAR (false alarm rate) while keeping the highest DR (detection rate). Additional experiments on real-world data show that IMIA-HCRF brings an improvement with the advantage of 11.5% FAR in average compared with the baselines.

Video traffic monitoring is an inexpensive and convenient source of traffic data. Traffic images processing are widely used to check traffic conditions and they can determine traffic control strategies in intelligent transportation systems (ITS). However, these traffic images always contain privacy-related data, such as vehicles registration numbers, human faces. Misuse of such data is a threat to the privacy of vehicles divers, passengers, pedestrians, etc. This paper proposes a thresholds-based images extraction solution for ITS. At first, a Faster Region Convolutional Neural Networks (RCNN) model is used to segment a traffic image into multi-regions with different importance levels; then, multi-threshold image extraction schemes are designed based on progressive secret image sharing schemes to extract images contain key traffic information, such as reg number, human faces, in which the region with higher importance level requires higher threshold for extraction. For different roles in ITS, they can extract images with different details, which can protect privacy and anonymity. The proposed methods provide a safe and intelligent way to extract images that can be used for further analysis in ITS.

Digital image forensics is a key branch of digital forensics that based on forensic analysis of image authenticity and image content. The advances in new techniques, such as smart devices, Internet of Things (IoT), artificial images, and social networks, make forensic image analysis play an increasing role in a wide range of criminal case investigation. This work focuses on image source identification by analysing both the fingerprints of digital devices and images in IoT environment. A new convolutional neural network (CNN) method is proposed to identify the source devices that token an image in social IoT environment. The experimental results show that the proposed method can effectively identify the source devices with high accuracy.

With the flourish of the Web 2.0, online reviews offer valuable information for customers and businesses. Deep investigation on the online reviews can help the businesses understand customers and their needs, which can assist decision making in product design and marketing. However, the massive records with irregular structure and ambiguous words pose great challenges for online review analysis. In this paper, we focus on the movie reviews and propose a framework to mine the aspect-based opinions, and utilize the results for decision making support. Based on the different sentence characteristics of movie reviews collected from Douban, the most popular movie community in China, we divide the reviews into two categories, short reviews and long reviews. Firstly, we develop different methods to extract the fine-grained aspects including the global and local aspects from the short reviews and long reviews respectively. Secondly, a lexical updating algorithm is proposed to identify the opinion words towards different aspects. In contrast to most studies that focus on determining the overall sentiment orientation (positive versus negative), the proposed method performs fine-grained analysis to mine both the various aspects and their corresponding opinions of a movie. Finally, based on the positive and negative opinions towards different aspects, the producers can improve the marketing strategy and future products. Experimental results based on the data collected from Douban verify the efficiency and accuracy of the developed methods.

The pervasiveness of personalized collaborative recommender systems has shown the powerful capability in a wide range of E-commerce services such as Amazon, TripAdvisor, Yelp, etc. However, fundamental vulnerabilities of collaborative recommender systems leave space for malicious users to affect the recommendation results as the attackers desire. A vast majority of existing detection methods assume certain properties of malicious attacks are given in advance. In reality, improving the detection performance is usually constrained due to the challenging issues: (a) various types of malicious attacks coexist, (b) limited representations of malicious attack behaviors, and (c) practical evidences for exploring and spotting anomalies on real-world data are scarce. In this paper, we investigate a unified detection framework in an eye for an eye manner without being bothered by the details of the attacks. Firstly, co-visitation and co-rating graphs are constructed using association rules. Then, attribute representations of nodes are empirically developed from the perspectives of linkage pattern, structure-based property and inherent association of nodes. Finally, both attribute information and connective coherence of graph are combined in order to infer suspicious nodes. Extensive experiments on both synthetic and real-world data demonstrate the effectiveness of the proposed detection approach compared with competing benchmarks. Additionally, abnormality forensics metrics including distribution of rating intention, time aggregation of suspicious ratings, degree distributions before as well as after removing suspicious nodes and time series analysis of historical ratings, are provided so as to discover interesting findings such as suspicious nodes (items or ratings) on real-world data.

Internet of Things (IoT) are increasingly common in our society, and can be found in civilian settings as well as sensitive applications, such as battlefields and national security. Given the potential of these devices to be targeted by attackers, they are a valuable source in digital forensic investigations. In addition, incriminating evidence may be stored on an IoT device (e.g., Amazon Echo in a home environment and Fitbit worn by the victim or an accused person). In comparison to IoT security and privacy literature, IoT forensics is relatively under-studied. IoT forensics is also challenging in practice, particularly due to the complexity, diversity, and heterogeneity of IoT devices and ecosystems. In this paper, we present an IoT-based forensic model that supports the identification, acquisition, analysis, and presentation of potential artifacts of forensic interest from IoT devices and the underpinning infrastructure. Specifically, we use the popular Amazon Echo as a use case to demonstrate how our proposed model can be used to guide forensics analysis of IoT devices.

In the harsh environmental conditions of cyber-physical systems (CPSs), the consensus problem seems to be one of the central topics that affect the performance of consensus-based applications, such as events detection, estimation, tracking, blockchain, etc. In this paper, we investigate the events detection based on consensus problem of CPS by means of compressed sensing (CS) for applications such as attack detection, industrial process monitoring, automatic alert system, and prediction for potentially dangerous events in CPS. The edge devices in a CPS are able to calculate a log-likelihood ratio (LLR) from local observation for one or more events via a consensus approach to iteratively optimize the consensus LLRs for the whole CPS system. The information-exchange topologies are considered as a collection of jointly connected networks and an iterative distributed consensus algorithm is proposed to optimize the LLRs to form a global optimal decision. Each active device in the CPS first detects the local region and obtains a local LLR, which then exchanges with its active neighbors. Compressed data collection is enforced by a reliable cluster partitioning scheme, which conserves sensing energy and prolongs network lifetime. Then the LLR estimations are improved iteratively until a global optimum is reached. The proposed distributed consensus algorithm can converge fast and hence improve the reliability with lower transmission burden and computation costs in CPS. Simulation results demonstrated the effectiveness of the proposed approach.

Cyber-physical social system (CPSS) plays an important role in both the modern lifestyle and business models, which significantly changes the way we interact with the physical world. The increasing influence of cyber systems and social networks is also a high risk for security threats. The objective of this paper is to investigate associated risks in CPSS, and a hybrid Bayesian risk graph (HBRG) model is proposed to analyze the temporal attack activity patterns in dynamic cyberphysical social networks. In the proposed approach, a hidden Markov model is introduced to model the dynamic influence of activities, which then be mapped into a Bayesian risks graph (BRG) model that can evaluate the risk propagation in a layered risk architecture. Our numerical studies demonstrate that the framework can model and evaluate risks of user activity patterns that expose to CPSSs.

Edge detection is a vital part in image segmentation. In this paper, a novel method based on adjacent dispersion for edge detection is proposed. This method utilizes adjacent dispersion to detect edges, avoiding thresholds selection, anisotropy in convolution computation and discontinuity in edges, and it is composed of two modules, namely the dispersion operator and the refinement. The dispersion is to obtain a matrix of discrete coefficient of a gray level image and the refinement is to thin edges to one-pixel-point and ensure it logically continuous. The performance of the proposed edge detector is evaluated on different test images and compared with popular edge detectors, Canny and Sobel. Experiment results indicate that the proposed method performs well without thresholds and offers superior performance in continuity in edge detection in digital images.

The problem of discovering influential users is important to understand and analyze online social networks. The user profiles and interactions between users are significant features to evaluate the user influence. As these features are heterogeneous, it is challengeable to take all of them into a proper model for influence evaluation. In this paper, we propose a model based on personal user features and the adjacent factor to discover influential users in online social networks. Through taking the advantages of Bayesian network and chain principle of PageRank algorithm, the features of the user profiles and interactions are integratedly considered in our model. Based on real data from Sina Weibo data and multiple evaluation metrics of retweet count, tweet count, follower count, etc., the experimental results show that influential users identified by our model are more powerful than the ones identified by single indicator methods and PageRank-based methods.

User interaction is one of the most important features of online social networks, and is the basis of research of user behavior analysis, information spreading model, etc. However, existing approaches focus on the interactions between adjacent nodes, which do not fully take the interactions and relationship between local region users into consideration as well as the details of interaction process. In this paper, we find that there exists influence transfer effect in the process of user interactions, and present a regional user interaction model to analyze and understand interactions between users in a local region by influence transfer effect. Based on real data from Sina Weibo, we validate the effectiveness of our model by the experiments of user type classification, influential user identification and zombie user identification in online social networks. The experimental results show that our model present better performance than the PageRank based method and machine learning method.