Unsupervised domain adaptation is the problem of transferring extracted knowledge from a labeled source domain to an unlabeled target domain. To achieve discriminative domain adaptation recent studies take advantage of target sample pseudo-labels to impose class-aware distribution alignment across the source and target domains. Still, they have some shortcomings such as making decisions based on inaccurate pseudo-labeled samples that mislead the adaptation process. In this paper, we propose a progressive deep feature alignment, called Norma, to tackle class-aware unsupervised domain adaptation for image classification by enforcing inter-class compactness and intra-class discrepancy through a hybrid learning process. To this end, Norma's optimization process is defined based on a novel triplet loss which not only addresses soft prototype alignment but also pushes away multiple negative centroids. Also, to extract maximum discriminative domain knowledge per iteration, we propose a joint positive and negative learning procedure along with an uncertainty-guided progressive pseudo-labeling on the basis of prototype-based clustering and conditional probability. Our experimental results on several benchmarks demonstrate that Norma outperforms the state-of-the-art methods.

The impact of marine life on the oceans of our planet is undeniable and overfishing is a serious threat to marine ecosystems worldwide. Maritime domain awareness calls for continuous monitoring and tracking of fisheries using data from maritime intelligence sources to detect illegal fishing activities. Marine traffic data from vessel tracking services is a promising source for identifying, locating, and capturing vessel information. Given the volume of such data, manual processing is impossible, raising an immediate need for autonomous and smart systems to follow the footprints of vessels and detect their activity types in near real-time. To achieve this goal, we propose FishNET, a simple yet effective convolutional neural network (CNN) model for vessel trajectory classification. The model is trained using a set of invariant spatiotemporal feature sequences extracted from the behavioral characteristics of vessel movements.

Nowadays, continuously operating critical services increasingly rely on complex cyber-physical systems, which are also known as high-profile targets of cyberattacks, potentially resulting in security breaches that can cause severe damage. This paper presents a novel study on detecting cyberattacks against distributed supervisory control systems. AttackTracker, a scalable and unsupervised analytic framework for behavior-based online intrusion detection, is organized as a hierarchical network of cooperating attack detectors. Each local attack detector monitors and reports the status of a subsystem by labeling observations, assigning attack scores, and raising red flags by comparing actual versus predicted signal values from the observed input stream. While higher-level detectors utilize information aggregated from detectors at lower levels to assess the global security status of the supervisory control system. Our experiments show that AttackTracker outperforms leading methods for detecting complex attacks in a real-world operational context and it can be used for intrusion detection across a wide range of cyber-physical systems.

Temporal causal discovery aims to find cause-effect relationships between time-series. However, none of the existing techniques is able to identify the causal profile, the temporal pattern that the causal variable needs to follow in order to trigger the most significant change in the outcome. Toward a new horizon, this study introduces the novel problem of Causal Profile Discovery, which is crucial for many applications such as adverse drug reaction and cyber-attack detection. This work correspondingly proposes Heidegger to discover causal profiles, comprised of a flexible randomized block design for hypothesis evaluation and an efficient profile search via on-the-fly graph construction and entropy-based pruning. Heidegger's performance is demonstrated/evaluated extensively on both synthetic and real-world data. The experimental results show the proposed method is robust to noise and flexible at detecting complex patterns.

In this paper we propose a data-driven approach to detection and tracking of dark fishing in high-volume marine traffic datasets from vessel tracking services. Dark fishing refers to stealthy fishing operations by vessels trying to hide their illicit activities related to various forms of illegal fishing-one of the most serious threats to world fisheries and fish populations worldwide as well as to global food security. Our approach builds on profiling and ranking fishing vessels by analyzing their routine operations over extended time periods to uncover abnormal activity patterns associated with dark fishing. The focus is on vessel movement patterns rendered as a trajectory with defined starting and endpoints such as ports and known anchorage locations. Specifically, we analyze scenarios where the fishing pattern, with the fishing gear in the water, is obscured in a vessel's reported trip data. Our experimental evaluation, using a large dataset of fishing vessel trajectories from coastal waters of North America, shows the effectiveness and efficiency of the proposed method in differentiating between suspicious and normal fishing vessels irrespective of the vessel type.

Intelligent monitoring and control of critical infrastructure such as electric power grids, public water utilities and transportation systems produces massive volumes of time series data from heterogeneous sensor networks. Time Series Forecasting (TSF) is essential for system safety and security, and also for improving the efficiency and quality of service delivery. Being highly dependent on various external factors, the observed system behavior is usually stochastic, which makes the next value prediction a tricky and challenging task that usually needs customized methods. In this paper we propose a novel deep learning based framework for time series analysis and prediction by ensembling parametric and nonparametric methods. Our approach takes advantage of extracting features at different time scales, which improves accuracy without compromising reliability in comparison with the state-of-the-art methods. Our experimental evaluation using real-world SCADA data from a municipal water management system shows that our proposed method outperforms the baseline methods evaluated here.

Considering the fact that fully immunizing critical infrastructure such as water supply or power grid systems against physical and cyberattacks is not feasible, it is crucial for every public or private sector to invigorate the detective, predictive, and preventive mechanisms to minimize the risk of disruptions, resource loss or damage. This paper proposes a methodical approach to situation analysis and anomaly detection in SCADA-based water supply systems. We model normal system behavior as a hierarchy of hidden semi-Markov models, forming the basis for detecting contextual anomalies of interest in SCADA data. Our experimental evaluation on real-world water supply system data emphasizes the efficacy of our method by significantly outperforming baseline methods.

Model-Driven Development (MDD) is a promising approach to software development, mainly due to the pivotal role of models in its process, and the high potential it provides for automated model/software generation. Since software processes can themselves be considered as software, any technique or approach applied in the context of software development is also of potential use in the development of software development processes. Accordingly, the MDD approach can potentially be applied in the context of Situational Method Engineering (SME) - a branch devoted to the study of developing bespoke software development processes and methods based on the specific characteristics of the development project at hand. The authors propose a Model-Driven Situational Method Engineering (MDSME) framework by defining different levels of abstraction for process models, in compliance to the multi-level model abstraction and transformation approach prescribed by the Model-Driven Architecture (MDA). The framework can be used by method engineers to construct custom software development methodologies through an MDD approach that facilitates automation, enhances the accuracy of the development process produced, and improves the portability of process models.