Biblio

As an emerging technology, IoT is rapidly revolutionizing the global communication network with billions of new devices deployed and connected with each other. Many of these devices collect and transfer a large amount of sensitive or mission critical data, making security a top priority. Compared to traditional Internet, IoT networks often operate in open and harsh environment, and may experience frequent delays, traffic loss and attacks; Meanwhile, IoT devices are often severally constrained in computational power, storage space, network bandwidth, and power supply, which prevent them from deploying traditional security schemes. Authentication is an important security mechanism that can be used to identify devices or users. Due to resource constrains of IoT networks, it is highly desirable for the authentication scheme to be lightweight while also being highly effective. In this paper, we developed and evaluated a hash-chain-based multi-node mutual authentication algorithm. Nodes on a network all share a common secret key and broadcast to other nodes in range. Each node may also add to the hash chain and rebroadcast, which will be used to authenticate all nodes in the network. This algorithm has a linear running time and complexity of O(n), a significant improvement from the O(nˆ2) running time and complexity of the traditional pairwise multi-node mutual authentication.

This paper uses the test tool provided by the Internet Protocol Version 6 (IPv6) Forum to test the protocol conformance of IPv6 devices. The installation and testing process of IPv6 Ready Logo protocol conformance test suite developed by TAHI PROJECT team is described in detail. This section describes the test content and evaluation criteria of the suite, analyzes the problems encountered during the installation and use of the suite, describes the method of analyzing the test results of the suite, and describes the test content added to the latest version of the test suite. The test suite can realize automatic testing, the test cases accurately reflect the requirements of the IPv6 protocol specification, can be used to judge whether IPv6-based Internet of Things(IoT) devices meets the relevant protocol standards.

Control room video surveillance is an important source of information for ensuring public safety. To facilitate the process, a Decision-Support System (DSS) designed for the security task force is vital and necessary to take decisions rapidly using a sea of information. In case of mission critical operation, Situational Awareness (SA) which consists of knowing what is going on around you at any given time plays a crucial role across a variety of industries and should be placed at the center of our DSS. In our approach, SA system will take advantage of the human factor thanks to the reinforcement signal whereas previous work on this field focus on improving knowledge level of DSS at first and then, uses the human factor only for decision-making. In this paper, we propose a situational awareness-centric decision-support system framework for mission-critical operations driven by Quality of Experience (QoE). Our idea is inspired by the reinforcement learning feedback process which updates the environment understanding of our DSS. The feedback is injected by a QoE built on user perception. Our approach will allow our DSS to evolve according to the context with an up-to-date SA.

In the context of cybersecurity systems, trust is the firm belief that a system will behave as expected. Trustworthiness is the proven property of a system that is worthy of trust. Therefore, trust is ephemeral, i.e. trust can be broken; trustworthiness is perpetual, i.e. trustworthiness is verified and cannot be broken. The gap between these two concepts is one which is, alarmingly, often overlooked. In fact, the pressure to meet with the pace of operations for mission critical cross domain solution (CDS) development has resulted in a status quo of high-risk, ad hoc solutions. Trustworthiness, proven through formal verification, should be an essential property in any hardware and/or software security system. We have shown, in "vCDS: A Virtualized Cross Domain Solution Architecture", that developing a formally verified CDS is possible. virtual CDS (vCDS) additionally comes with security guarantees, i.e. confidentiality, integrity, and availability, through the use of a formally verified trusted computing base (TCB). In order for a system, defined by an architecture description language (ADL), to be considered trustworthy, the implemented security configuration, i.e. access control and data protection models, must be verified correct. In this paper we present the first and only security auditing tool which seeks to verify the security configuration of a CDS architecture defined through ADL description. This tool is useful in mitigating the risk of existing solutions by ensuring proper security enforcement. Furthermore, when coupled with the agile nature of vCDS, this tool significantly increases the pace of system delivery.

This work proposed a unified approach to increase the explainability of the predictions made by Convolution Neural Networks (CNNs) on medical images using currently available Explainable Artificial Intelligent (XAI) techniques. This method in-cooperates multiple techniques such as LISA aka Local Interpretable Model Agnostic Explanations (LIME), integrated gradients, Anchors and Shapley Additive Explanations (SHAP) which is Shapley values-based approach to provide explanations for the predictions provided by Blackbox models. This unified method increases the confidence in the black-box model’s decision to be employed in crucial applications under the supervision of human specialists. In this work, a Chest X-ray (CXR) classification model for identifying Covid-19 patients is trained using transfer learning to illustrate the applicability of XAI techniques and the unified method (LISA) to explain model predictions. To derive predictions, an image-net based Inception V2 model is utilized as the transfer learning model.

The error-resiliency of Artificial Intelligence (AI) hardware accelerators is a major concern, especially when they are deployed in mission-critical and safety-critical applications. In this paper, we propose a neuron fault tolerance strategy for Spiking Neural Networks (SNNs). It is optimized for low area and power overhead by leveraging observations made from a large-scale fault injection experiment that pinpoints the critical fault types and locations. We describe the fault modeling approach, the fault injection framework, the results of the fault injection experiment, the fault-tolerance strategy, and the fault-tolerant SNN architecture. The idea is demonstrated on two SNNs that we designed for two SNN-oriented datasets, namely the N-MNIST and IBM's DVS128 gesture datasets.

The increased use of Convolutional Neural Networks (CNN) in mission-critical systems has increased the need for robust and resilient networks in the face of both naturally occurring faults as well as security attacks. The lack of robustness and resiliency can lead to unreliable inference results. Current methods that address CNN robustness require hardware modification, network modification, or network duplication. This paper proposes MILR a software-based CNN error detection and error correction system that enables recovery from single and multi-bit errors. The recovery capabilities are based on mathematical relationships between the inputs, outputs, and parameters(weights) of the layers; exploiting these relationships allows the recovery of erroneous parameters (iveights) throughout a layer and the network. MILR is suitable for plaintext-space error correction (PSEC) given its ability to correct whole-weight and even whole-layer errors in CNNs.

We present a novel approach for the collaborative training of neural network models in decentralized federated environments. In the iterative process a group of autonomous peers run multiple training rounds to train a common model. Thereby, participants perform all model training steps locally, such as stochastic gradient descent optimization, using their private, e.g. mission-critical, training datasets. Based on locally updated models, participants can jointly determine a common model by averaging all associated model weights without sharing the actual weight values. For this purpose we introduce a simple n-out-of-n secret sharing schema and an algorithm to calculate average values in a peer-to-peer manner. Our experimental results with deep neural networks on well-known sample datasets prove the generic applicability of the approach, with regard to model quality parameters. Since there is no need to involve a central service provider in model training, the approach can help establish trustworthy collaboration platforms for businesses with high security and data protection requirements.

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party data (e.g., data from the Internet or third-party data company). This raises the question of whether adopting untrusted third-party data can pose a security threat. In this paper, we demonstrate that it is possible to inject the hidden backdoor for infecting speaker verification models by poisoning the training data. Specifically, we design a clustering-based attack scheme where poisoned samples from different clusters will contain different triggers (i.e., pre-defined utterances), based on our understanding of verification tasks. The infected models behave normally on benign samples, while attacker-specified unenrolled triggers will successfully pass the verification even if the attacker has no information about the enrolled speaker. We also demonstrate that existing back-door attacks cannot be directly adopted in attacking speaker verification. Our approach not only provides a new perspective for designing novel attacks, but also serves as a strong baseline for improving the robustness of verification methods. The code for reproducing main results is available at https://github.com/zhaitongqing233/Backdoor-attack-against-speaker-verification.

FastChain is a simulator built in NS-3 which simulates the networked battlefield scenario with military applications, connecting tankers, soldiers and drones to form Internet-of-Battlefield-Things (IoBT). Computing, storage and communication resources in IoBT are limited during certain situations in IoBT. Under these circumstances, these resources should be carefully combined to handle the task to accomplish the mission. FastChain simulator uses Sharding approach to provide an efficient solution to combine resources of IoBT devices by identifying the correct and the best set of IoBT devices for a given scenario. Then, the set of IoBT devices for a given scenario collaborate together for sharding enabled Blockchain technology. Interested researchers, policy makers and developers can download and use the FastChain simulator to design, develop and evaluate blockchain enabled IoBT scenarios that helps make robust and trustworthy informed decisions in mission-critical IoBT environment.

Cyber-physical systems are an integral component of weapons, sensors and autonomous vehicles, as well as cyber assets directly supporting tactical forces. Mission resilience of tactical networks affects command and control, which is important for successful military operations. Traditional engineering methods for mission assurance will not scale during battlefield operations. Commanders need useful mission resilience metrics to help them evaluate the ability of cyber assets to recover from incidents to fulfill mission essential functions. We develop 6 cyber resilience metrics for tactical network architectures. We also illuminate how psychometric modeling is necessary for future research to identify resilience metrics that are both applicable to the dynamic mission state and meaningful to commanders and planners.