Manufacturers in the automotive industry extensively rely on iterative process Failure Mode and Effects Analysis (FMEA) in their quality management. Process FMEAs model technical impacts based on engineering artifacts. However, traditional process FMEA methods are typically document-centric and do not integrate feedback from the shop floor without significant delay. In this paper, we introduce the Digital Shadow for Production Quality Analysis (DS-PQA) method and system design that integrates feedback from machine components on the shop floor. To this end, the method leverages FMEA and production system engineering models to configure OPC Unified Architecture (OPC UA)-based data acquisition. Based on that data acquisition, the DS-PQA system analyzes data from the shop floor to (i) inform operators on likely causes of a production defect, and (ii) alert FMEA experts about FMEA causes that occur more frequently than expected and should be re-validated. In a feasibility study, we evaluated the effectiveness and efficiency of the DS-PQA method and system on a welding cell that manufactures automotive parts. The study results indicate that the DS-PQA method and system are feasible, more efficient, and can substantially lower the latency for analyzing production quality risk compared to a traditional approach.

In agile Cyber-physical Production System (CPPS) engineering, multi-disciplinary teams work concurrently and iteratively on various CPPS engineering artifacts, based on engineering models and Product-Process-Resource (PPR) knowledge, to design and build a production system. However, in such settings it is difficult to keep track of (i) the effects of changes across engineering disciplines, and (ii) their implications on risks to engineering quality, represented in Failure Mode and Effects Analysis (FMEA). To tackle these challenges and systematically co-evolve FMEA and PPR models, requires propagating and validating changes across engineering and FMEA artifacts. To this end, we design and evaluate a Multi-view FMEA +PPR (MvFMEA+PPR) meta-model to represent relationships between FMEA elements and CPPS engineering assets and trace their change states and dependencies in the design and validation lifecycle. We evaluate the MvFMEA + PPR meta-model in a feasibility study on the quality of a screwing process from automotive production. The study results indicate the MvFMEA + PPR meta-model to be more effective than alternative traditional approaches.

During the ramp-up of a production system, complex and difficult to resolve product quality issues often result in tedious experimentation and costly delays. A particular challenge in this context is insufficient guidance for operators on how to resolve issues and adapt their actions to a new production context. Failure Mode and Effects Analysis (FMEA) can help to identify and address likely causes of production quality issues. However, FMEA models are typically (i) isolated from engineering domain models on product, process and resource (PPR) concerns, and (ii) not actionable for operators. This paper introduces the FMEA-to-Operation (F2O) approach to reduce the risk of ramp-up delays and recurring quality issues by integrating the required domain knowledge for model-driven, machine skill-centric, and actionable process FMEA. The F2O approach (i) validates likely root causes of a production quality issue by linking these causes to engineering reality in a graph database, and (ii) derives operation checklists with prioritized countermeasures. In a feasibility study on a real-world welding cell for car parts, we evaluated the effectiveness and efficiency of the F2O approach. Results indicate that the F2O approach is feasible and effective, and provides operators with actionable, context-specific guidelines that are well grounded in engineering models.

Attack graph-based methods are a promising approach towards discovering attacks and various techniques have been proposed recently. A key limitation, however, is that approaches developed so far are monolithic in their architecture and heterogeneous in their internal models. The inflexible custom data models of existing prototypes and the implementation of rules in code rather than declarative languages on the one hand make it difficult to combine, extend, and reuse techniques, and on the other hand hinder reuse of security knowledge – including detection rules and threat intelligence. KRYSTAL tackles these challenges by providing a knowledge graph-based, modular framework for threat detection, attack graph and scenario reconstruction, and analysis based on RDF as a standard model for knowledge representation. This approach provides query options that facilitate contextualization over internal and external background knowledge, as well as the integration of multiple detection techniques, including tag propagation, attack signatures, and graph queries. We implemented our framework in an openly available prototype and demonstrate its applicability on multiple scenarios of the DARPA Transparent Computing dataset. Our evaluation shows that the combination of different threat detection techniques within our framework improved detection capabilities. Furthermore, we find that RDF provenance graphs are scalable and can efficiently support a variety of threat detection techniques.

Security professionals rely extensively on log data to monitor IT infrastructures and investigate potentially malicious activities. Existing systems support these tasks by collecting log messages in a database, from where log events can be queried and correlated. Such centralized approaches are typically based on a relational model and store log messages as plain text, which offers limited flexibility for the representation of heterogeneous log events and the connections between them. A knowledge graph representation can overcome such limitations and enable graph pattern-based log analysis, leveraging semantic relationships between objects that appear in heterogeneous log streams. In this paper, we present a method to dynamically construct such log knowledge graphs at query time, i.e., without a priori parsing, aggregation, processing, and materialization of log data. Specifically, we propose a method that – for a given query formulated in SPARQL – dynamically constructs a virtual log knowledge graph directly from heterogeneous raw log files across multiple hosts and contextualizes the result with internal and external background knowledge. We evaluate the approach across multiple heterogeneous log sources and machines and see encouraging results that indicate that the approach is viable and facilitates ad-hoc graph-analytic queries in federated settings.

In Cyber-physical Production System (CPPS) engineering, data analysts and domain experts collaborate to identify likely causes for quality issues. Industry 4.0 production assets can provide a wealth of data for analysis, making it difficult to identify the most relevant data. Because data analysts typically do not posses detailed knowledge of the production process, a key challenge is to discover potential causes that impact product quality with various experts, as knowledge about production processes is typically distributed across various domains. To address this, we highlight the need for cross-domain modelling and outline an approach for effective and efficient quality analysis. Specifically, we introduce the Quality Dependency Graph (QDG) to represent cross-domain knowledge dependencies for efficiently prioritizing data sources. We evaluate the QDG in a feasibility study based on a real-world use case in the automotive industry.

Abstract This paper introduces an evolving cybersecurity knowledge graph that integrates and links critical information on real-world vulnerabilities, weaknesses and attack patterns from various publicly available sources. Cybersecurity constitutes a particularly interesting domain for the development of a domain-specific public knowledge graph, particularly due to its highly dynamic landscape characterized by time-critical, dispersed, and heterogeneous information. To build and continually maintain a knowledge graph, we provide and describe an integrated set of resources, including vocabularies derived from well-established standards in the cybersecurity domain, an ETL workflow that updates the knowledge graph as new information becomes available, and a set of services that provide integrated access through multiple interfaces. The resulting semantic resource offers comprehensive and integrated up-to-date instance information to security researchers and professionals alike. Furthermore, it can be easily linked to locally available information, as we demonstrate by means of two use cases in the context of vulnerability assessment and intrusion detection.

The growth of Linked Data has created a promising environment for data exploration and a growing number of tools allow users to interactively integrate data from various sources. Eliciting the reliability of the results of such ad-hoc integration processes, consistently recreating those results, and identifying changes upon re-execution, however, can be difficult. Automated process provenance trail creation can provide major benefits in this context, because (i) it enables users to trace the contribution of individual sources and processing steps to the final outcome and judge whether the result can be trusted; (ii) it ensures repeatability and raises the trustworthiness of results; (iii) it ideally enables reconstruction of Linked Data integration processes from the provenance information embedded in the final result. In this paper, we present a provenance model that facilitates automatic generation of semantic provenance information for generic Linked Data integration processes. We implement the generic model in a collaborative mashup environment and evaluate it by means of an example application. We find that the model provides a solid foundation for verifiability and contributes towards making Linked Data integration processes more open, transparent, and reusable, which is crucial in domains where the origin of data is essential, such as, for instance, statistical analyses, scientific research, and data journalism.

Despite an abundance of data available on the web today, satisfying users' complex information needs intelligently by automatically integrating and processing data from various sources remains challenging. In recent years, a large stream of research into mashups as a paradigm of end user development has emerged. These mashups foster combination and reuse of data and services and thereby allow end users to create novel applications. Developing such mashups efficiently and effectively, however, is still difficult for users that lack technical expertise. To address this issue, we extend a mashup platform with automatic mashup composition mechanisms and an agent that assists users in mashup design. To this end, we leverage semantics to simplify the mashup composition process on multiple levels. We associate each widget (i.e., mashup component) with a semantic model of inputs and outputs. These semantic models are helpful for identifying appropriate widgets in a given context and allow us to validate the links between widgets in a mashup. These validations provide the foundation for an advanced composition algorithm that automatically creates meaningful mashups from a given set of widgets. Finally, we develop an agent that leverages the semantic annotations to allow users to automatically compose mashups by entering natural-language text.

Today, public statistical data plays an increasingly important role both in public policy formation and as a facilitator for informed decision-making in the private sector. In line with to the increasing adoption of open data policies, the amount of data published by governments and organizations on the web is growing rapidly. To make such data more useful, the W3C has developed the RDF Data Cube Vocabulary to facilitate the publication of data in a more structured and interlinked manner. Although important first steps toward building a web of statistical linked datasets have been made, however, providing adequate facilities for end users to interactively explore and make use of the published data largely remains an unresolved challenge. This paper presents a widget-based approach to deal with this issue. In particular, we introduce a mashup platform that allows users without advanced skills and knowledge of Semantic Web technologies to interactively analyze datasets through widget compositions and visualizations. Furthermore, we provide mechanisms for the interconnection of datasets to support sophisticated knowledge extraction.

Whereas the number of open and accessible data sources on the web is growing rapidly, data becomes more heterogeneous and is difficult to use or reuse. Even though many national and international organizations have published their data according to the Linked Data principles, a considerable number of data sources is still available in traditional formats, e.g., HTML, XML, CSV, JSON. This results in a challenge of data aggregation and integration. To address this issue, we apply the visual programming paradigm to develop an open web platform. The platform is based on Semantic Web technologies and aims at encouraging and facilitating use of heterogeneous Open Data sources. We define Linked Widgets as user-driven modules which support users in accessing, processing, integrating, and visualizing different kinds of data. By connecting Linked Widgets from different developers, users without programming skills can compose and share ad-hoc applications that combine Open Data sources in a creative manner.

Discrete multi-criteria decision problems with numerous Pareto-efficient solution candidates place a significant cognitive burden on the decision maker. An interactive, aspiration-based search process that iteratively progresses toward the most preferred solution can alleviate this task. In this paper, we study three ways of representing such problems in a DSS, and compare them in a laboratory experiment using subjective and objective measures of the decision process as well as solution quality and problem understanding. In addition to an immediate user evaluation, we performed a re-evaluation several weeks later. Furthermore, we consider several levels of problem complexity and user characteristics. Results indicate that different problem representations have a considerable influence on search behavior, although long-term consistency appears to remain unaffected. We also found interesting discrepancies between subjective evaluations and objective measures. Conclusions from our experiments can help designers of DSS for large multi-criteria decision problems to fit problem representations to the goals of their system and the specific task at hand.

In this paper, we report on our ongoing research on simulation-based information security risk assessment and multi-objective optimization of investment in security controls. We outline a methodological framework that accounts for characteristics of the organization, its information infrastructure, assets to be protected, the particular threat sources it faces, and the decision-makers' risk preferences. This framework comprises (i) ontological modeling of security knowledge, (ii) dynamic attack graph generation techniques, (iii) probabilistic simulation of attacks by goal-driven threat agents, (iv) meta-heuristic identification of efficient portfolios of information security controls, and (v) interactive decision support. These components facilitate novel techniques to infer possible routes of attacks and generate attack graphs based on attackers' motivation, objectives, capabilities, and available modes of entry and to use this inferred knowledge to simulate attacks on an organization's modeled infrastructure. The method supports decision makers evaluating potential security control investments in striking a balance between monetary and non-monetary criteria regarding risks, costs, and benefits. We are currently in the process of developing a prototypical implementation of the framework that will be used to evaluate the approach through application case studies.

Kiesling E, Günther M, Stummer C, Vetschera R, Wakolbinger LM. A spatial simulation model for the diffusion of a novel biofuel on the Austrian market. In: Bargiela A, Azam-Ali S, Crowley D, Kerckhoffs EJH, eds. Proceedings of the 24th European Conference on Modelling and Simulation (ECMS 2010). 2010: 41-49.