Vessel trajectory prediction is fundamental to intelligent maritime systems. Within this domain, short-term prediction of rapid behavioral changes in complex maritime environments has established multimodal trajectory prediction (MTP) as a promising research area. However, existing vessel MTP methods suffer from limited scenario applicability and insufficient explainability. To address these challenges, we propose a unified MTP framework incorporating explainable navigation intentions, which we classify into sustained and transient categories. Our method constructs sustained intention trees from historical trajectories and models dynamic transient intentions using a Conditional Variational Autoencoder (CVAE), while using a non-local attention mechanism to maintain global scenario consistency. Experiments on real Automatic Identification System (AIS) datasets demonstrates our method’s broad applicability across diverse scenarios, achieving significant improvements in both ADE and FDE. Furthermore, our method improves explainability by explicitly revealing the navigational intentions underlying each predicted trajectory.

Gradient leakage attacks pose a significant privacy threat in distributed learning-as-a-service APIs. Existing literature on gradient leakage defense relies on gradient perturbation for preventing privacy leakage. However, determining where and how much to perturb the gradient offers different capabilities for preventing gradient leakage. This paper presents GradCloak, a principled approach to guiding gradient perturbation with theoretical robustness bounds in federated learning as a service, aiming to find the minimum required noise for simultaneously achieving privacy protection, competitive accuracy, and preventing gradient leakage attacks. The paper is organized into three major components.First, we formulate the gradient leakage threats and their adverse effect. We categorize the attack into two broad types: leakage during local training and leakage before global aggregation.Second, we investigate different gradient perturbation approaches. We analyze and compare these gradient perturbation methods, which are performed at the federated server, with those performed at the participating client(s).Third, we introduce three robustness properties of robust perturbation against gradient leakage threats, formulated bythe anonymization boundfor training data robustness,the perturbation boundfor gradient robustness, andthe distribution robustness boundfor perturbed gradients. We conduct extensive evaluations on eight benchmark datasets to demonstrate that specific settings of gradient perturbation exist that best balance privacy, accuracy, and leakage prevention. Code is available athttps://github.com/git-disl/GradCloak.

Machine Learning (ML) techniques have been applied to many real-world applications to perform a wide range of tasks. In practice, ML models are typically deployed as the black-box APIs to protect the model owner’s benefits and/or defend against various privacy attacks. In this paper, we present Gradient-Leaks as the first evidence showcasing the possibility of performing membership inference attacks (MIAs), with mere black-box access, which aim to determine whether a data record was utilized to train a given target ML model or not. The key idea of Gradient-Leaks is to construct a local ML model around the given record which locally approximates the target model’s prediction behavior. By extracting the membership information of the given record from the gradient of the substituted local model using an intentionally modified autoencoder, Gradient-Leaks can thus breach the membership privacy of the target model’s training data in an unsupervised manner, without any priori knowledge about the target model’s internals or its training data. Extensive experiments on different types of ML models with real-world datasets have shown that Gradient-Leaks can achieve a better performance compared with state-of-the-art attacks.

Vessel trajectory clustering, which aims to find similar trajectory patterns, has been widely leveraged in maritime applications. Most traditional methods use predefined rules and thresholds to identify discrete vessel behaviors. They aim for high-quality clustering and conduct clustering on entire sequences, whether the original trajectory or its sub-trajectories, overlooking the behavioral significance and evolution characteristics. To resolve this problem, we propose a Predictive Clustering of Hierarchical Vessel Behavior (PC-HiV). PC-HiV first utilizes hierarchical representations to transform every trajectory into a behavioral sequence. It then predicts evolution at each timestamp of the sequence based on the representations. By applying predictive clustering and latent encoding, PC-HiV improves clustering and predictions simultaneously. Experiments conducted on real AIS datasets demonstrate that PC-HiV effectively captures behavioral evolution discrepancies between different vessel types (tramp vs. liner) and near emission control area boundaries. Additionally, the results show that PC-HiV outperforms NN-Kmeans and Robust DAA by 3.9% and 6.4% in terms of purity scores, thereby proving the superiority of the proposed PC-HiV over existing models.

Point-of-interest (POI) recommendation service has drawn growing attention with the widespread popularity of location- based social networks (LBSNs). Recent research methods on POI recommendation based on graph embedding have mainly focused on explicit interactions of LBSN objects such as user's check-ins on POIs and social relationships, while neglecting implicit relationship that cannot be directly observed but may notably contribute to the POI recommendation. This paper presents VirHpoi, a heterogeneous hypergraph embedding method for POI recommendation in LBSNs with three original contributions. First, we model the LBSNs as a hypergraph to capture the complex interactions in LBSNs and learn the hypergraph by preserving homophily and interaction attribute affinity of the LBSNs. Second, we introduce the notion of “virtual hyperedges” to capture the intrinsic correlations of POIs. Virtual hyperedges incorporate implicit yet informative connections of the check-in patterns in LBSNs in terms of geographical and semantic characteristics. Third, we propose techniques to learn heterogenous hypergraph embedding on the complex LBSN graph with both homogenous edges and heterogenous hyperedges with dual objectives: we aim to preserve the homophily of objects intra domain by maximizing the co-occurrence probability of all homogenous edges, and we want to learn the interaction attribute affinity across domains by maximizing the probability of predicting the target object in the hyperedges. As a result, our approach can preserve both the intra domain homophily of objects and the interaction attribute affinity across domains by learning low-dimensional embeddings of LBSN objects and then make more effective recommendations based on the embeddings. Extensive experiments on four real-world datasets show the effectiveness and superiority of VirHpoi compared with the state-of-the-art methods.

The graph-based hyperspectral image classification (HSIC) method has attracted wide attention because it can extract information with a non-Euclidean structure. Many graph-based HSIC works have achieved good results, but unresolved technical issues remain. For example, many graph nodes lead to high computational costs, and the mining of non-Euclidean structures is not sufficient. To solve these problems, we propose a graph attention network with an adaptive graph structure mining (GAT-AGSM) approach. Specifically, we first propose an HSIC framework with a superpixel feature subdivision (SFS) mechanism. In this framework, the number of nodes in the graph structure is reduced by using superpixel segmentation algorithms, and the SFS mechanism is designed to generate finer classification results. Second, we design the spatial–spectral attention layer with an adaptive graph structure mining (AGSM) mechanism for the graph attention network. The spatial–spectral attention layer can filter information in both spatial and spectral dimensions. The AGSM mechanism requires less manual intervention to dynamically generate non-Euclidean graph structures that better aggregate information. We conduct excessive experiments to compare the proposed GAT-AGSM with seven nongraph methods and three graph-based methods on widely used datasets. On the Indian Pines, Pavia University, and Salinas datasets, compared to the comparison method, the overall accuracy of GAT-AGSM is improved by at least 4.26%, 2.59%, and 1.41%, respectively. Experimental results show that GAT-AGSM has the best performance compared to the baselines in terms of various metrics.

Taxi arrival time prediction is essential for building intelligent transportation systems. Traditional prediction methods mainly rely on extracting features from traffic maps, which cannot model complex situations and nonlinear spatial and temporal relationships. Therefore, we propose Multi-View Spatial-Temporal Model (MVSTM) to capture the mutual dependence of spatial-temporal relations and trajectory features. Specifically, we use graph2vec to model the spatial view, dual-channel temporal module to model the trajectory view, and structural embedding to model traffic semantics. Experiments on large-scale taxi trajectory data have shown that our approach is more effective than the existing novel methods. The source code can be found at https://github.com/775269512/SIGSPATIAL-2021-GISCUP-4th-Solution.

With the development of location-based services (LBS), concerns on location privacy frequently arise. Location data often contains users' sensitive information, and direct release it may pose a threat to users' privacy. Differential privacy (DP), as a privacy preserving method with solid mathematical foundation, has been widely used in location data release. However, most if not all of the existing location DP mechanisms only consider static scenarios or perturb the location at single timestamp, which are vulnerable to the so-called location-dependent attacks (LDA) in continuous LBS queries. In this paper, an optimal location DP mechanism against LDA is proposed. Firstly, the necessary conditions for LDA defense are derived by combining the perturbation mechanism of location DP. Then the algorithm of safe perturbance region generation is established to dynamically calculate the perturbation range at each timestamp. Finally, we set up the optimization problem with the real-time quality loss as the optimization objective and the location DP and safe perturbance region as the optimization conditions, and realize the optimal DP mechanism for LDA by solving the optimization problem. Experiment results on real-world datasets show that our mechanism can effectively resist LDA, which also balance privacy protection and data utility well.

Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can disrupt the learning procedure by injecting a fraction of malicious samples into the training dataset. Existing defense techniques against poisoning attacks are largely attack-specific: they are designed for one specific type of attacks but do not work for other types, mainly due to the distinct principles they follow. Yet few general defense strategies have been developed. In this paper, we propose De-Pois, an attack-agnostic defense against poisoning attacks. The key idea of De-Pois is to train a mimic model the purpose of which is to imitate the behavior of the target model trained by clean samples. We take advantage of Generative Adversarial Networks (GANs) to facilitate informative training data augmentation as well as the mimic model construction. By comparing the prediction differences between the mimic model and the target model, De-Pois is thus able to distinguish the poisoned samples from clean ones, without explicit knowledge of any ML algorithms or types of poisoning attacks. We implement four types of poisoning attacks and evaluate De-Pois with five typical defense methods on different realistic datasets. The results demonstrate that De-Pois is effective and efficient for detecting poisoned data against all the four types of poisoning attacks, with both the accuracy and F1-score over 0.9 on average.

Recommender systems (RS) have become an essential component of web services due to their excellent performance. Despite their great success, RS have proved to be vulnerable to data poisoning attacks, which inject well-crafted fake profiles into RS, so that the target items can be maliciously recommended. In this paper, we first reveal that existing poisoning attacks in RS can be detected effortlessly, as the features of the generated fake profiles cannot be inconsistent with those of normal profiles all the time. We further propose RecUP, a poisoning attack in RS that can generate plausible profiles whose features stay almost the same as the normal ones, based on Generative Adversarial Networks (GAN). To tailor GAN for poisoning in RS, we develop HRGAN and devise a loss function to guide the training of the generator, along with a masking operation with selected potentially powerful profiles, so that the final generated profiles can perform malicious recommendations as expected. Evaluations against various defense methods using three real-world datasets show that, RecUP can generate the most plausible profiles while maintaining comparable attacking performance compared with state-of-the-art attacks.

GPS-dependent localization, navigation and air traffic control (ATC) applications have had a significant impact on the modern aviation industry. However, the lack of encryption and authentication makes GPS vulnerable to spoofing attacks with the purpose of hijacking aerial vehicles or threatening air safety. In this paper, we propose GPS-Probe, a GPS spoofing detection algorithm that leverages the ATC messages that are periodically broadcasted by aerial vehicles. By continuously analyzing the received signal strength indicator (RSSI) and the timestamps at server (TSS) of the ATC messages, which are monitored by multiple ground sensors, GPS-Probe constructs a machine learning enabled framework to estimate the real position of the target aerial vehicle and to detect whether or not the position data is compromised by GPS spoofing attacks. Unlike existing techniques, GPS-Probe neither requires any updates of the GPS infrastructure nor updates of the GPS receivers. More importantly, it releases the requirement on time synchronization of the ground sensors distributed around the world. Using the real-world ATC data crowdsourced by the OpenSky Network, our experiment results show that GPS-Probe can achieve the detection accuracy and precision, of 81.7% and 85.3% respectively on average, and up to 89.7% and 91.5% respectively at the best.

Trajectory clustering aims at grouping similar trajectories into one cluster. It is an efficient way of finding the representative path or common trend shared by different moving objects, and also provides a foundation for movement pattern mining, anomaly detection and other applications. Existing trajectory clustering studies mainly rely on feature selection and similarity measurement based on their geographical and spatial properties. However, one obstacle hindering their wide usage is the problem of clustering accuracy in the presence of noisy or incomplete sensing data, due to limited sensory device quantity, communication errors, sensor failures, and sensor vacancy. This paper proposes an error-tolerant trajectory clustering approach by incorporating denoising methods.We propose the Robust Deep Attention Auto-encoders model (called Robust DAA) to learn the representations of low-dimensional denoising trajectories with three novel features. First, we present the deep attention auto-encoders by integrating the attention mechanism into the classical deep auto-encoder, which is capable of enhancing feature propagation and feature selection. Second, we train the deep attention auto-encoder by applying proximal method, back propagation and the Alternating Direction of Method of Multipliers (ADMM). As a result, our Robust DAA can reduce the negative influence of the noise on trajectory data. Finally, we perform clustering over the low-dimensional denoising representations using traditional clustering algorithms and demonstrates the quality of the clustering results by comparing our approach with existing representative methods. Extensive experiments are conducted on both synthetic datasets and real datasets. The results show that our approach outperforms the existing models in terms of accuracy, precision, recall and f1-score.

Temporal regularity in trajectory data is an important basis for traffic management, public service and marketing. Although many efforts have been made to study temporal regularity, yet almost all existing works select time granularity intuitively. User-specified time granularity and other parameters may lead to biased results. Moreover, as the size of datasets grows, the costs of parameters tuning also increases. To solve these problems, we propose the Automatic Multi-granularity Temporal Regularity Detection algorithm (auto-MTRD) for trajectory data. Our approach clusters time series from the trajectory data using automatic parameter selection and generates a temporal regularity tree to indicate multi-granularity temporal regularity. It cannot only avoid the negative effect of human intervention, but also evaluate the relative importance of multiple time granularities at the same time. Two real-life datasets are used to validate the effectiveness of our method.

When emergencies happen, navigation services that guide people to exits while keeping them away from emergencies are critical in saving lives. To achieve timely emergency navigation, early and automatic detection of potential dangers, and quick response with safe paths to exits are the core requirements, both of which rely on continuous environment monitoring and reliable data transmission. Wireless sensor networks (WSNs) are a natural choice of the infrastructure to support emergency navigation services, given their relatively easy deployment and affordable costs, and the ability of ubiquitous sensing and communication. Although many efforts have been made to WSN-assisted emergency navigation, almost all existing works neglect to consider the hazard levels of emergencies and the evacuation capabilities of exits. Without considering such aspects, existing navigation approaches may fail to keep people farther away from emergencies of high hazard levels and would probably encounter congestions at exits with lower evacuation capabilities. In this paper, we propose SEND, a situation-aware emergency navigation algorithm, which takes the hazard levels of emergencies and the evacuation capabilities of exits into account and provides the mobile users the safest navigation paths accordingly. We formally model the situation-aware emergency navigation problem and establish a hazard potential field in the network, which is theoretically free of local minima. By guiding users following the descend gradient of the hazard potential field, SEND can thereby achieve guaranteed success of navigation and provide optimal safety. The effectiveness of SEND is validated by both experiments and extensive simulations in 2D and 3D scenarios.

All online social networks gather data that reflects users' profiles, interactive behaviors and shared activities. This data can be used to extract users' interests and make recommendations. According to abundant personal data, recommenders can identify information relevant for individuals. To reveal users' different preferences explicitly, we present a rule-based method which supports different recommendation strategies. Moreover, we also show that this method is effective by conducting experiments on real data.

The concept of universal network measurement environment (UNME) is proposed, which includes three entities, i.e., the name server, the monitoring center and the probe. The architecture that the entities follow is called the universal network measurement (UNM), which consists of three layers. The key technologies such as component management protocol, network measurement policy protocol and the network measurement cooperative layer are explored and the construction of the probe and the method how to change measurement tools into the UNM probes are introduced. Finally, a real network monitoring & measurement system following UNM is illustrated, and several network measurement applications built on it are introduced.