Biblio

Explainable Artificial Intelligence (XAI), i.e., the development of more transparent and interpretable AI models, has gained increased traction over the last few years. This is due to the fact that, in conjunction with their growth into powerful and ubiquitous tools, AI models exhibit one detrimental characteristic: a performance-transparency trade-off. This describes the fact that the more complex a model's inner workings, the less clear it is how its predictions or decisions were achieved. But, especially considering Machine Learning (ML) methods like Reinforcement Learning (RL) where the system learns autonomously, the necessity to understand the underlying reasoning for their decisions becomes apparent. Since, to the best of our knowledge, there exists no single work offering an overview of Explainable Reinforcement Learning (XRL) methods, this survey attempts to address this gap. We give a short summary of the problem, a definition of important terms, and offer a classification and assessment of current XRL methods. We found that a) the majority of XRL methods function by mimicking and simplifying a complex model instead of designing an inherently simple one, and b) XRL (and XAI) methods often neglect to consider the human side of the equation, not taking into account research from related fields like psychology or philosophy. Thus, an interdisciplinary effort is needed to adapt the generated explanations to a (non-expert) human user in order to effectively progress in the field of XRL and XAI in general.

Operators of cyber-physical systems (CPSs) need to maintain awareness of the cyber situation in order to be able to adequately address potential issues in a timely manner. For instance, detecting early symptoms of cyber attacks may speed up the incident response process and mitigate consequences of attacks (e.g., business interruption, safety hazards). However, attaining a full understanding of the cyber situation may be challenging, given the complexity of CPSs and the ever-changing threat landscape. In particular, CPSs typically need to be continuously operational, may be sensitive to active scanning, and often provide only limited in-depth analysis capabilities. To address these challenges, we propose to utilize the concept of digital twins for enhancing cyber situational awareness. Digital twins, i.e., virtual replicas of systems, can run in parallel to their physical counterparts and allow deep inspection of their behavior without the risk of disrupting operational technology services. This paper reports our work in progress to develop a cyber situational awareness framework based on digital twins that provides a profound, holistic, and current view on the cyber situation that CPSs are in. More specifically, we present a prototype that provides real-time visualization features (i.e., system topology, program variables of devices) and enables a thorough, repeatable investigation process on a logic and network level. A brief explanation of technological use cases and outlook on future development efforts completes this work.

The XML-based data format AutomationML enables vendor-independent exchange of design data between discipline-specific design tools. It is based on Computer Aided Engineering Exchange (CAEX) and hence, compatible with the W3C standards XMLEnc (XML encryption) and XMLDsig (XML signatures). However, despite the importance of protecting engineering data, so far no concept has been presented to ensure and control on a fine-grained level the confidentiality, authenticity and accessibility of information stored in AutomationML files. In this paper, we introduce a basic access control scheme for AutomationML that enables to define user read and write access for each component. Furthermore, the scheme supports non-repudiation based on a change history and so-called "signature chains". It is also capable of supporting views and restricted access to components. The scheme is based on cryptographic measures – i.e. cryptographic hashing, symmetric encryption, signatures, and asymmetric encryption – and enforces its access control mechanisms through encryption to protect against unauthorized reading, and through signature chains to protect against unauthorized manipulation and to ensure non-repudiation. This approach has the benefit to be independent of the underlying file and operating system, storage location, etc., and it keeps full CAEX-conformity by extending AutomationML.This concept can serve as basis for software tools that support AutomationML and want to integrate access control features directly into AutomationML.

As the connectivity within manufacturing processes increases in light of Industry 4.0, information security becomes a pressing issue for product suppliers, systems integrators, and asset owners. Reaching new heights in digitizing the manufacturing industry also provides more targets for cyber attacks, hence, cyber-physical production systems (CPPSs) must be adequately secured to prevent malicious acts. To achieve a sufficient level of security, proper defense mechanisms must be integrated already early on in the systems' lifecycle and not just eventually in the operation phase. Although standardization efforts exist with the objective of guiding involved stakeholders toward the establishment of a holistic industrial security concept (e.g., IEC 62443), a dedicated security development lifecycle for systems integrators is missing. This represents a major challenge for engineers who lack sufficient information security knowledge, as they may not be able to identify security-related activities that can be performed along the production systems engineering (PSE) process. In this paper, we propose a novel methodology named Security Development Lifecycle for Cyber-Physical Production Systems (SDL-CPPS) that aims to foster security by design for CPPSs, i.e., the engineering of smart production systems with security in mind. More specifically, we derive security-related activities based on (i) security standards and guidelines, and (ii) relevant literature, leading to a security-improved PSE process that can be implemented by systems integrators. Furthermore, this paper informs domain experts on how they can conduct these security-enhancing activities and provides pointers to relevant works that may fill the potential knowledge gap. Finally, we review the proposed approach by means of discussions in a workshop setting with technical managers of an Austrian-based systems integrator to identify barriers to adopting the SDL-CPPS.

Technical debt is an analogy introduced in 1992 by Cunningham to help explain how intentional decisions not to follow a gold standard or best practice in order to save time or effort during creation of software can later on lead to a product of lower quality in terms of product quality itself, reliability, maintainability or extensibility. Little work has been done so far that applies this analogy to cyber physical (production) systems (CP(P)S). Also there is only little work that uses this analogy for security related issues. This work aims to fill this gap: We want to find out which security related symptoms within the field of cyber physical production systems can be traced back to TD items during all phases, from requirements and design down to maintenance and operation. This work shall support experts from the field by being a first step in exploring the relationship between not following security best practices and concrete increase of costs due to TD as consequence.

Despite the importance of databases in virtually all data driven applications, database forensics is still not the thriving topic it ought to be. Many database management systems (DBMSs) structure the data in the form of trees, most notably B+-Trees. Since the tree structure is depending on the characteristics of the INSERT-order, it can be used in order to generate information on later manipulations, as was shown in a previously published approach. In this work we analyse this approach and investigate, whether it is possible to generalize it to detect DELETE-operations within general INSERT-only trees. We subsequently prove that almost all forms of B+-Trees can be constructed solely by using INSERT-operations, i.e. that this approach cannot be used to prove the existence of DELETE-operations in the past.

The rapid deployment of IoT systems on the public Internet is not without concerns for the security and privacy of consumers. Security in IoT systems is often poorly engineered and engineering for privacy does notseemtobea concern for vendors at all. Thecombination of poor security hygiene and access to valuable knowledge renders IoT systems a much-sought target for attacks. IoT systems are not only Internet-accessible but also play the role of servers according to the established client-server communication model and are thus configured with static and/or easily predictable IPv6 addresses, rendering them an easy target for attacks. We present 6HOP, a novel addressing scheme for IoT devices. Our proposal is lightweight in operation, requires minimal administration overhead, and defends against reconnaissance attacks, address based correlation as well as denial-of-service attacks. 6HOP therefore exploits the ample address space available in IPv6 networks and provides effective protection this way.