Biblio

Anomalous behaviour in subsystems of complex machines often affect overall performance even without failures. We devise unsupervised methods to detect times with degraded performance, and localize correlated signals, evaluated on a system with over 4000 monitored signals. From incidents comprising both downtimes and degraded performance, our approach localizes relevant signals within 1.2% of the parameter space.

Internet of Things (IoT) networks consist of small devices that use a wireless communication to monitor and possibly control the physical world. A common threat to such networks are jamming attacks, a particular type of denial of service attack. Current research highlights the need for the design of more effective and efficient anti-jamming techniques that can handle different types of attacks in IoT networks. In this paper, we propose DeMiJA, short for Detection and Mitigation of Jamming Attacks in IoT, a novel approach to deal with different jamming attacks in IoT networks. DeMiJA leverages architecture-based adaptation and the MAPE-K reference model (Monitor-Analyze-Plan-Execute that share Knowledge). We present the general architecture of DeMiJA and instantiate the architecture to deal with jamming attacks in the DeltaIoT exemplar. The evaluation shows that DeMiJA can handle different types of jamming attacks effectively and efficiently, with neglectable overhead.

In the context of IoT (Internet of Things), Device Management (DM), i.e., remote administration of IoT devices, becomes essential to keep them connected, updated and secure, thus increasing their lifespan through firmware and configuration updates and security patches. Legacy DM solutions are adequate when dealing with home devices (such as Television set-top boxes) but need to be extended to adapt to new IoT requirements. Indeed, their manual operation by system administrators requires advanced knowledge and skills. Further, the static DM platform — a component above IoT platforms that offers advanced features such as campaign updates / massive operation management — is unable to scale and adapt to IoT dynamicity. To cope with this, this work, performed in an industrial context at Orange, proposes a self-adaptive architecture with runtime horizontal scaling of DM servers, with an autonomic Auto-Scaling Manager, integrating in the loop constraint programming for decision-making, validated with a meaningful industrial use-case.

Machine Learning (ML) models are now commonly used as components in systems. As any other component, ML components can produce erroneous outputs that may penalize system utility. In this context, self-adaptive systems emerge as a natural approach to cope with ML mispredictions, through the execution of adaptation tactics such as model retraining. To synthesize an adaptation strategy, the self-adaptation manager needs to reason about the cost-benefit tradeoffs of the applicable tactics, which is a non-trivial task for tactics such as model retraining, whose benefits are both context- and data-dependent.To address this challenge, this paper proposes a probabilistic modeling framework that supports automated reasoning about the cost/benefit tradeoffs associated with improving ML components of ML-based systems. The key idea of the proposed approach is to decouple the problems of (i) estimating the expected performance improvement after retrain and (ii) estimating the impact of ML improved predictions on overall system utility.We demonstrate the application of the proposed framework by using it to self-adapt a state-of-the-art ML-based fraud-detection system, which we evaluate using a publicly-available, real fraud detection dataset. We show that by predicting system utility stemming from retraining a ML component, the probabilistic model checker can generate adaptation strategies that are significantly closer to the optimal, as compared against baselines such as periodic retraining, or reactive retraining.

Distributed computation and AI processing at the edge has been identified as an efficient solution to deliver real-time IoT services and applications compared to cloud-based paradigms. These solutions are expected to support the delay-sensitive IoT applications, autonomic decision making, and smart service creation at the edge in comparison to traditional IoT solutions. However, existing solutions have limitations concerning distributed and simultaneous resource management for AI computation and data processing at the edge; concurrent and real-time application execution; and platform-independent deployment. Hence, first, we propose a novel three-layer architecture that facilitates the above service requirements. Then we have developed a novel platform and relevant modules with integrated AI processing and edge computer paradigms considering issues related to scalability, heterogeneity, security, and interoperability of IoT services. Further, each component is designed to handle the control signals, data flows, microservice orchestration, and resource composition to match with the IoT application requirements. Finally, the effectiveness of the proposed platform is tested and have been verified.

OHODIN is an online extension for data streams of the kNN-based ODIN anomaly detection approach. It provides a detection-threshold heuristic that is based on extreme value theory. In contrast to sophisticated anomaly and novelty detection approaches the decision-making process of ODIN is interpretable by humans, making it interesting for certain applications. However, it is limited in terms of the underlying detection method. In this article, we present an extension of the OHODIN to further detection techniques to reinforce OHODIN capability of online data streams anomaly detection. We introduce the algorithm modifications and an experimental evaluation with competing state-of-the-art anomaly detection approaches.

Resilience and antifragility under duress present significant challenges for autonomic and self-adaptive systems operating in contested environments. In such settings, the system has to continually plan ahead, accounting for either an adversary or an environment that may negate its actions or degrade its capabilities. This will involve projecting future states, as well as assessing recovery options, counter-measures, and progress towards system goals. For antifragile systems to be effective, we envision three self-* properties to be of key importance: self-exploration, self-learning and self-training. Systems should be able to efficiently self-explore – using adversarial search – the potential impact of the adversary’s attacks and compute the most resilient responses. The exploration can be assisted by prior knowledge of the adversary’s capabilities and attack strategies, which can be self-learned – using opponent modelling – from previous attacks and interactions. The system can self-train – using reinforcement learning – such that it evolves and improves itself as a result of being attacked. This paper discusses those visions and outlines their realisation in AWaRE, a cyber-resilient and self-adaptive multi-agent system.

The service mesh is a dedicated infrastructure layer in a microservice architecture. It manages service-to-service communication within an application between decoupled or loosely coupled microservices (called services) without modifying their implementations. The service mesh includes APIs for security, traffic and policy management, and observability features. These features are enabled using a pre-defined configuration, which can be changed at runtime with human intervention. However, it has no autonomy to self-manage changes to the microservice application’s operational environment. A better configuration is one that can be customized according to environmental conditions during execution to protect the application from potential threats. This customization requires enabling self-protection mechanisms within the service mesh that evaluate the risk of environmental condition changes and enable appropriate configurations to defend the application from impending threats. In this paper, we design an assessment component into a service mesh that includes a security assurance case to define the threat model and dynamically assess the application given environment changes. We experiment with a demo application, Bookinfo, using an open-source service mesh platform, Istio, to enable self-protection. We consider certain parameters extracted from the service request as environmental conditions. We evaluate those parameters against the threat model and determine the risk of violating a security requirement for controlled and authorized information flow.

Unmanned autonomous vehicles (UAVs) have been receiving high interest lately due to their wide range of potential deployment options that can touch all aspects of our life and economy, such as transportation, delivery, healthcare, surveillance. However, UAVs have also introduced many new vulnerabilities and attack surfaces that can be exploited by cyberattacks. Due to their complexity, autonomous operations, and being relatively new technologies, cyberattacks can be persistent, complex, and can propagate rapidly to severely impact the main UAV functions such as mission management, support, processing operations, maneuver operations, situation awareness. Furthermore, such cyberattacks can also propagate among other UAVs or even their control stations and may even endanger human life. Hence, we need self-protection techniques with an autonomic management approach. In this paper we present our approach to implement self-protection of UAVs (SP-UAV) such that they can continue their critical functions despite cyberattacks targeting UAV operations or services. We present our design approach and implementation using a unified management interface based on three ports: Configuration, observer, and control ports. We have implemented the SP-UAV using C and demonstrated using different attack scenarios how we can apply autonomic responses without human involvement to tolerate cyberattacks against the UAV operations.

In the world of information technology and the Internet, which has become a part of human life today and is constantly expanding, Attention to the users' requirements such as information security, fast processing, dynamic and instant access, and costs savings has become essential. The solution that is proposed for such problems today is a technology that is called cloud computing. Today, cloud computing is considered one of the most essential distributed tools for processing and storing data on the Internet. With the increasing using this tool, the need to schedule tasks to make the best use of resources and respond appropriately to requests has received much attention, and in this regard, many efforts have been made and are being made. To this purpose, various algorithms have been proposed to calculate resource allocation, each of which has tried to solve equitable distribution challenges while using maximum resources. One of these calculation methods is the DRF algorithm. Although it offers a better approach than previous algorithms, it faces challenges, especially with time-consuming resource allocation computing. These challenges make the use of DRF more complex than ever in the low number of requests with high resource capacity as well as the high number of simultaneous requests. This study tried to reduce the computations costs associated with the DRF algorithm for resource allocation by introducing a new approach to using this DRF algorithm to automate calculations by machine learning and artificial intelligence algorithms (Autonomic Dominant Resource Fairness or A-DRF).

Container security has received much research attention recently. Previous work has proposed to apply various machine learning techniques to detect security attacks in containerized applications. On one hand, supervised machine learning schemes require sufficient labelled training data to achieve good attack detection accuracy. On the other hand, unsupervised machine learning methods are more practical by avoiding training data labelling requirements, but they often suffer from high false alarm rates. In this paper, we present SHIL, a self-supervised hybrid learning solution, which combines unsupervised and supervised learning methods to achieve high accuracy without requiring any manual data labelling. We have implemented a prototype of SHIL and conducted experiments over 41 real world security attacks in 28 commonly used server applications. Our experimental results show that SHIL can reduce false alarms by 39-91% compared to existing supervised or unsupervised machine learning schemes while achieving a higher or similar detection rate.

Nowadays, an increasing trend to use autonomous Unmanned Aerial Vehicles (UAV) for applications like logistics as well as security and surveillance can be recorded. Autonomic UAVs require robust and precise navigation to ensure efficient and safe operation even in strong multipath environments and (intended) interference. The need for robust navigation on UAVs implies the necessary integration of low-cost, lightweight, and compact array antennas as well as structures for multipath mitigation into the UAV platform. This article investigates a miniaturized antenna array mounted on top of vertical choke rings for robust navigation purposes. The array employs four 3D printed elements based on dielectric resonators capable of operating in all GNSS bands while compact enough for mobile applications such as UAV.

Adaptive authentication systems identify and enforce suitable methods to verify that someone (user) or something (device) is eligible to access a service or a resource. An authentication method is usually adapted in response to changes in the security risk or the user's behaviour. Previous work on adaptive authentication systems provides limited guidance about i) what and how contextual factors can affect the selection of an authentication method; ii) which requirements are relevant to an adaptive authentication system and iii) how authentication methods can affect the satisfaction of the relevant requirements. In this paper, we provide a holistic framework informed by previous research to characterize the adaptive authentication problem and support the development of an adaptive authentication system. Our framework explicitly considers the contextual factors that can trigger an adaptation, the requirements that are relevant during decision making and their trade-offs, as well as the authentication methods that can change as a result of an adaptation. From the gaps identified in the literature, we elicit a set of challenges that can be addressed in future research on adaptive authentication.

The pervasive use of software systems and current threat environment demand that software systems not only survive cyberattacks, but also bounce back better, stronger, and faster. However, what constitutes a modern software system? Where should the security and resilience mechanisms be-in the application software or in the cloud environment where it runs? In this concept paper, we set up a context to pose these questions and present a roadmap to answer them. We describe challenges to achieving resilience and beyond, and outline potential research directions to stimulate discussion in the workshop.

Semantic data has semantic information about the relationship between information and resources of data collected in a smart city so that all different domains and data can be organically connected. Various services using semantic data such as public data integration of smart cities, semantic search, and linked open data are emerging, and services that open and freely use semantic data are also increasing. By using semantic data, it is possible to create a variety of services regardless of platform and resource characteristics. However, despite the many advantages of semantic data, it is not easy to use because it requires a high understanding of semantics such as SPARQL. Therefore, in this paper, we propose a semantic framework for users of semantic data so that new services can be created without a high understanding of semantics. The semantics framework includes a template-based annotator that supports automatically generating semantic data based on user input and a semantic REST API that allows you to utilize semantic data without understanding SPAROL.

Software defined networking (SDN) architecture frame- work eases the work of the network administrators by separating the data plane from the control plane. This provides a programmable interface for applications development related to security and management. The centralized logical controller provides more control over the total network, which has complete network visibility. These SDN advantages expose the network to vulnerabilities and the impact of the attacks is much severe when compared to traditional networks, where the network devices have protection from the attacks and limits the occurrence of attacks. In this paper, we proposed an entropy based algorithm in SDN to detect as well as stopping distributed denial of service (DDoS) attacks on the servers or clouds or hosts. Firstly, there explored various attacks that can be launched on SDN at different layers. Basically DDoS is one kind of denial of service attack in which an attacker uses multiple distributed sources for attacking a particular server. Every network in a system has an entropy and an increase in the randomness of probability causes entropy to decrease. In comparison with previous entropy based approaches this approach has higher performance in distinguishing legal and illegal traffics and blocking illegal traffic paths. Linux OS and Mininet Simulator along with POX controller are used to validate the proposed approach. By conducting pervasive simulation along with theoretical analysis this method can definitely detect and stop DDoS attacks automatically.

Assuring Cybersecurity for the Internet of things (IoT) remains a significant challenge. Most IoT devices have minimal computational power and should be secured with lightweight security techniques (optimized computation and energy tradeoff). Furthermore, IoT devices are mainly designed to have long lifetimes (e.g., 10–15 years), forcing the designers to open the system for possible future updates. Here, we developed a lightweight and reconfigurable security architecture for IoT devices. Our research goal is to create a simple authentication protocol based on physical unclonable function (PUF) for FPGA-based IoT devices. The main challenge toward realization of this protocol is to make it make it resilient against machine learning attacks and it shall not use cryptography primitives.

The envisioned massive deployment of network slices in 5G and beyond mobile systems makes the shift towards zero-touch, scalable and secure slice lifecycle management a necessity. This is to harvest the benefits of network slicing in enabling profitable services. These benefits will not be attained without ensuring a high level security of the created network slices and the underlying infrastructure, above all in a zero-touch automated fashion. In this vein, this paper presents the architecture of an innovative network slicing security orchestration framework, being developed within the EU H2020 MonB5G project. The framework leverages the potential of Security as a Service (SECaaS) and Artificial Intelligence (AI) to foster fully-distributed, autonomic and fine-grained management of network slicing security from the node level to the end-to-end and inter-slice levels.

A service-based system (SBS) dynamically composes third-party services to deliver comprehensive functionality. As adaptive systems, SBSs can substitute equivalent services within the composition if service operations or workflow requirements change. Substituted services must maintain the original SBS quality of service (QoS) constraints. In this paper, we add security as a QoS constraint. Using a model problem of a SBS system created for self-adaptive system technology evaluation, we demonstrate the applicability of security assurance cases and service security profile exchange to build in security awareness for more informed SBS adaptation.

This paper is a systemization of knowledge of autonomic cybersecurity. Disruptive technologies, such as IoT, AI and autonomous systems, are becoming more prevalent and often have little or no cybersecurity protections. This lack of security is contributing to the expanding cybersecurity attack surface. The autonomic computing initiative was started to address the complexity of administering complex computing systems by making them self-managing. Autonomic systems contain attributes to address cyberattacks, such as self-protecting and self-healing that can secure new technologies. There has been a number of research projects on autonomic cybersecurity, with different approaches and target technologies, many of them disruptive. This paper reviews autonomic computing, analyzes research on autonomic cybersecurity, and provides a systemization of knowledge of the research. The paper concludes with identification of gaps in autonomic cybersecurity for future research.

Anomaly detection is critically important for intelligent surveillance systems to detect in a timely manner any malicious activities. Many video anomaly detection approaches using deep learning methods focus on a single camera video stream with a fixed scenario. These deep learning methods use large-scale training data with large complexity. As a solution, in this paper, we show how to use pre-trained convolutional neural net models to perform feature extraction and context mining, and then use denoising autoencoder with relatively low model complexity to provide efficient and accurate surveillance anomaly detection, which can be useful for the resource-constrained devices such as edge devices of the Internet of Things (IoT). Our anomaly detection model makes decisions based on the high-level features derived from the selected embedded computer vision models such as object classification and object detection. Additionally, we derive contextual properties from the high-level features to further improve the performance of our video anomaly detection method. We use two UCSD datasets to demonstrate that our approach with relatively low model complexity can achieve comparable performance compared to the state-of-the-art approaches.

With the expansion of Internet of Things (IoT) that relies on heterogeneous, dynamic, and massively deployed devices, device management (DM) (i.e., remote administration such as firmware update, configuration, troubleshooting and tracking) is required for proper quality of service and user experience, deployment of new functions, bug corrections and security patches distribution. Existing industrial DM platforms and approaches do not suit IoT devices and are already showing their limits with a few static home devices (e.g., routers, TV Decoders). Indeed, undetected buggy firmware deployment and manual target device identification are common issues in existing systems. Besides, these platforms are manually operated by experts (e.g., system administrators) and require extensive knowledge and skills. Such approaches cannot be applied on massive and diverse devices forming the IoT. To tackle these issues, our work in an industrial research context proposes to apply autonomic computing to DM platforms operation and impact tracking. Specifically, our contribution relies on automated device targeting (i.e., aiming only suitable devices) and impact-aware DM (i.e., error and anomalies detection preceding patch generalization on all suitable devices of a given fleet). Our solution is composed of three coordinated autonomic loops and allows more accurate and faster irregularity diagnosis, vertical scaling along with simpler IoT DM platform administration. For experimental validation, we developed a prototype that demonstrates encouraging results compared to simulated legacy telecommunication operator approaches (namely Orange).

This paper describes an approach to the security fault tolerance of access control in which the security breaches of an access control are tolerated by means of a security fault tolerant (SFT) access control. Though an access control is securely designed and implemented, it can contain faults in development or be contaminated in operation. The threats to an access control are analyzed to identify possible security breaches. To tolerate the security breaches, an SFT access control is made to be semantically identical to an access control. Our approach is described using role-based access control (RBAC) and extended access control list (EACL). A healthcare system is used to demonstrate our approach.

Attack-awareness recognizes self-awareness for security systems regarding the occurring attacks. More frequent and intense attacks on cloud and network infrastructures are pushing security systems to the limit. With the end of Moore's Law, merely scaling against these attacks is no longer economically justified. Previous works have already dealt with the adoption of Software-defined Networking and Network Function Virtualization in security systems and used both approaches to optimize performance by the intelligent placement of security functions. In our previous works, we already made a case for taking the order of security functions into account and dynamically adapt this order. In this work, we propose a reordering framework, provide a proof-of-concept implementation, and validate this implementation in an evaluation environment. The framework's evaluation proves the feasibility of our concept.

Since the birth of the Internet, the quality of network service has been a widespread concerned problem. With the continuous development of communication and information technology, people gradually realized that the contradiction between the limited resources and the business requirements of network cannot be fundamentally solved. In this paper, we design and develop a distributed security quality of service testing framework called AweQoS(AwesomeQoS), to adapt to the current complex network environment. This paper puts forward the necessity that some security tests should be closely combined with quality of service testing, and further discusses the basic methods of distributed denial of service attack and defense. We introduce the design idea and working process of AweQoS in detail, and introduce a bandwidth test method based on user datagram protocol. Experimental results show that this new test method has better test performance and potential under the AweQoS framework.