Biblio

An experimental network environment plays an important role to examine new systems and protocols. We have developed an experimental network construction tool called LiONv1 (Lightweight On-Demand Networking, ver.1). LiONv1 satisfies the following four requirements: programmer-friendly configuration file based on Infrastructure as Code, multiple virtualization technologies for virtual nodes, physical topology conscious virtual node placement, and L3 protocol agnostic virtual networks. None of existing experimental network environments satisfy all the four requirements. In this paper, we develop LiONv2 which satisfies three more requirements: diversity of available network devices, Internet-scale deployment, and disaggregation of network configuration and device configuration. LiONv2 employs NETCONF and YANG to achieve diversity of available network devices and Internet-scale deployment. LiONv2 also defines two YANG models which disaggregate network configuration and device configuration. LiONv2 is implemented in Go and C languages with public libraries for Go. Measurement results show that construction time of a virtual network is irrelevant to the number of virtual nodes if a single virtual node is created per physical node.

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.

Hardware counters are included in processors to count microarchitecture level events affecting performance. When control flow anomalies caused by attacks such as buffer overflow or return oriented programming (ROP) occur, they leave a microarchitectural footprint. Hardware counters reflect such footprints to flag control flow anomalies. This paper is geared towards buffer overflow and ROP control flow anomaly detection in embedded programs. The targeted program entities are main event loops and task/event handlers. Embedded systems also have enhanced need for variable anomaly detection time in order to meet the system response time requirements. We propose a novel repurposing of Patt-Yeh two level branch predictor data structure for abstracting/hashing HW counter signatures to support such variable anomaly detection times. The proposed anomaly detection mechanism is evaluated on some generic benchmark programs and ArduPilot - a popular autopilot software. Experimental evaluation encompasses both Intel X86 and ARM Cortex M processors. DWT within Cortex M provides sufficiently interesting program level event counts to capture these control flow anomalies. We are able to achieve 97-99%+ accuracy with 1-10 micro-second time overhead per anomaly check.

Due to the wide deployment of deep learning applications in safety-critical systems, robust and secure execution of deep learning workloads is imperative. Adversarial examples, where the inputs are carefully designed to mislead the machine learning model is among the most challenging attacks to detect and defeat. The most dominant approach for defending against adversarial examples is to systematically create a network architecture that is sufficiently robust. Neural Architecture Search (NAS) has been heavily used as the de facto approach to design robust neural network models, by using the accuracy of detecting adversarial examples as a key metric of the neural network's robustness. While NAS has been proven effective in improving the robustness (and accuracy in general), the NAS-generated network models run noticeably slower on typical DNN accelerators than the hand-crafted networks, mainly because DNN accelerators are not optimized for robust NAS-generated models. In particular, the inherent multi-branch nature of NAS-generated networks causes unacceptable performance and energy overheads.To bridge the gap between the robustness and performance efficiency of deep learning applications, we need to rethink the design of AI accelerators to enable efficient execution of robust (auto-generated) neural networks. In this paper, we propose a novel hardware architecture, NASGuard, which enables efficient inference of robust NAS networks. NASGuard leverages a heuristic multi-branch mapping model to improve the efficiency of the underlying computing resources. Moreover, NASGuard addresses the load imbalance problem between the computation and memory-access tasks from multi-branch parallel computing. Finally, we propose a topology-aware performance prediction model for data prefetching, to fully exploit the temporal and spatial localities of robust NAS-generated architectures. We have implemented NASGuard with Verilog RTL. The evaluation results show that NASGuard achieves an average speedup of 1.74× over the baseline DNN accelerator.

In this paper, we investigate a networked control problem in the presence of Denial-of-Service (DoS) attacks, which prevent transmissions over the communication network. The communication between the process and controller is also subject to bit rate constraints. For mitigating the influences of DoS attacks and bit rate constraints, we develop a variable bit rate (VBR) encoding-decoding protocol and quantized controller to stabilize the control system. We show that the system’s resilience against DoS under VBR is preserved comparing with those under constant bit rate (CBR) quantized control, with fewer bits transmitted especially when the attack levels are low. The proposed VBR quantized control framework in this paper is general enough such that the results of CBR quantized control under DoS and moreover the results of minimum bit rate in the absence of DoS can be recovered.

Physical-layer security (PLS) for an underlay cognitive radio network (CRN)-based simultaneous wireless information and power transfer (SWIPT) over cascaded κ-µ fading channels is investigated. The network is composed of a pair of secondary users (SUs), a primary user (PU) receiver, and an eavesdropper attempting to intercept the data shared by the SUs. To improve the SUs’ data transmission security, we assume a full-duplex (FD) SU destination, which employs energy harvesting (EH) to extract the power required for generating jamming signals to be emitted to confound the eavesdropper. Two scenarios are presented and compared; harvesting and non-harvesting eavesdropper. Moreover, a trade-off between the system’s secrecy and reliability is explored. PLS is studied in terms of the probability of non-zero secrecy capacity and the intercept probability, whereas the reliability is studied in terms of the outage probability. Results reveal the great impact of jamming over the improvement of the SUs’ secrecy. Additionally, our work indicates that studying the system’s secrecy over cascaded channels has an influence on the system’s PLS that cannot be neglected.

The 5G network systems are evolving and have complex network infrastructures. There is a great deal of work in this area focused on meeting the stringent service requirements for the 5G networks. Within this context, security requirements play a critical role as 5G networks can support a range of services such as healthcare services, financial and critical infrastructures. 3GPP and ETSI have been developing security frameworks for 5G networks. Our work in 5G security has been focusing on the design of security architecture and mechanisms enabling dynamic establishment of secure and trusted end to end services as well as development of mechanisms to proactively detect and mitigate security attacks in virtualised network infrastructures. The focus of this paper is on the latter, namely the facilities and mechanisms, and the design of a security architecture providing facilities and mechanisms to detect and mitigate specific security attacks. We have developed a simplified version of the security architecture using Software Defined Networks (SDN) and Network Function Virtualisation (NFV) technologies. The specific security functions developed in this architecture can be directly integrated into the 5G core network facilities enhancing its security.

The design of attacks for cyber physical systems is critical to assess CPS resilience at design time and run-time, and to generate rich datasets from testbeds for research. Attacks against cyber physical systems distinguish themselves from IT attacks in that the main objective is to harm the physical system. Therefore, both cyber and physical system knowledge are needed to design such attacks. The current practice to generate attacks either focuses on the cyber part of the system using IT cyber security existing body of knowledge, or uses heuristics to inject attacks that could potentially harm the physical process. In this paper, we present a systematic approach to automatically generate integrity attacks from the CPS safety and control specifications, without knowledge of the physical system or its dynamics. The generated attacks violate the system operational and safety requirements, hence present a genuine test for system resilience. We present an algorithm to automate the malware payload development. Several examples are given throughout the paper to illustrate the proposed approach.

Physical layer authentication (PLA) has recently been discussed in the context of URLLC due to its low complexity and low overhead. Nevertheless, these schemes also introduce additional sources of error through missed detections and false alarms. The trade-offs of these characteristics are strongly dependent on the deployment scenario as well as the processing architecture. Thus, considering a feature-based PLA scheme utilizing channel-state information at multiple distributed radio-heads, we study these trade-offs analytically. We model and analyze different scenarios of centralized and decentralized decision-making and decoding, as well as the impacts of a single-antenna attacker launching a Sybil attack. Based on stochastic network calculus, we provide worst-case performance bounds on the system-level delay for the considered distributed scenarios under a Sybil attack. Results show that the arrival-rate capacity for a given latency deadline is increased for the distributed scenarios. For a clustered sensor deployment, we find that the distributed approach provides 23% higher capacity when compared to the centralized scenario.

Satisfying security requirements for Mobile Ad-hoc Networks (MANETs) is a key challenge due to the limited power budget for the nodes composing those networks. Therefore, it is essential to exploit lightweight cryptographic algorithms to preserve the confidentiality of the messages being transmitted between different nodes in MANETs. At the heart of such algorithms lies the Elliptic Curve Cryptography (ECC). The importance of ECC lies in offering equivalent security with smaller key sizes, which results in faster computations, lower power consumption, as well as memory and bandwidth savings. However, when exploiting ECC in MANETs, it is essential to properly choose the parameters of ECC such that an acceptable level of confidentiality is achieved without entirely consuming the power budget of nodes. In addition, the delay of the communication should not abruptly increase. In this paper, we study the effect of changing the prime number use in ECC on power consumption, delay, and the security of the nodes in MANETs. Once a suitable prime number is chosen, a comparative analysis is conducted between two reactive routing protocols, namely, Ad-hoc on Demand Distance Vector (AODV) and Dynamic Source Routing (DSR) in terms of power consummation and delay. Experimental results show that a prime number value of 197 for ECC alongside with DSR for routing preserve an acceptable level of security for MANETs with low average power consumption and low average delay in the communication.

Wireless sensor networks (WSNs) are underlying network infrastructure for a variety of surveillance applications. The network should be tolerant of unexpected failures of sensor nodes to meet the Quality of Service (QoS) requirements of these applications. One major cause of failure is active security attacks such as Depletion-of-Battery (DoB) attacks. This paper model the problem of detecting such attacks as an anomaly detection problem in a dynamic graph. The problem is addressed by employing a cluster ensemble approach called the K-Means Spectral and Hierarchical ensemble (KSH) approach. The experimental result shows that KSH detected DoB attacks with better accuracy when compared to baseline approaches.

During this period of high-speed internet, there are a number of serious challenges for software security protection of software design, especially throughout the life cycle of the process of software design, in which there are various risks involving information interaction. Significant information leakage can result from a lack of technical support and software security protection. One major problem with regard to creating software that includes security is the way that secure software is defined and the methods that are used for the measurement of security. The point of this research work is on the software engineers' perspective regarding security in the stage of software design. The tools for the measurement of the metrics are employed for the evaluation of the software's security. In this case study, a metric category of design are used, which are assumed to provide quantitative data about the software's security.

Cloud Computing is a technology which provides flexibility through scalability. Like, Cloud computing, nowadays, Fog computing is considered more revolutionary and dynamic technology. But the main problem with the Fog computing is to take care of its security as in this also person identification is done by single Sign-In system. To come out from the security problem raised in Fog computing, an innovative approach has been suggested here. In the present paper, an approach has been proposed that combines different biometric techniques to verify the authenticity of a person and provides a complete model that will be able to provide a necessary level of verification and security in fog computing. In this model, several biometric techniques have been used and each one of them individually helps extract out more authentic and detailed information after every step. Further, in the presented paper, different techniques and methodologies have been examined to assess the usefulness of proposed technology in reducing the security threats. The paper delivers a capacious technique for biometric authentication for bolstering the fog security.

In order to realize Intelligent Disaster Recovery and break the traditional reactive backup mode, it is necessary to forecast the potential system anomalies, and proactively backup the real-time datas and configurations. System logs record the running status as well as the critical events (including errors and warnings), which can help to detect system performance, debug system faults and analyze the causes of anomalies. What's more, with the features of real-time, hierarchies and easy-access, log data can be an ideal source for monitoring system status. To reduce the complexity and improve the robustness and practicability of existing log-based anomaly detection methods, we propose a new anomaly detection mechanism based on hierarchical weights, which can deal with unstable log data. We firstly extract semantic information of log strings, and get the word-level weights by SIF algorithm to embed log strings into vectors, which are then feed into attention-based Long Short-Term Memory(LSTM) deep learning network model. In addition to get sentence-level weight which can be used to explore the interdependence between different log sequences and improve the accuracy, we utilize attention weights to help with building workflow to diagnose the abnormal points in the execution of a specific task. Our experimental results show that the hierarchical weights mechanism can effectively improve accuracy of perdition task and reduce complexity of the model, which provides the feasibility foundation support for Intelligent Disaster Recovery.

This paper presents the application of Compressive Sampling (CS) to the realization of a wideband receiver for distributed spectrum monitoring. The proposed prototype performs the non-uniform sampling CS-based technique, while the signal reconstruction is realized by the Orthogonal Matching Pursuit (OMP) algorithm on a personal computer. A first experimental analysis has been conducted on the prototype by assessing several figures of merit, thus characterizing its performance in the time, frequency and modulation domains. The obtained results demonstrate that the proposed prototype can achieve good performance in all specified domains with Compression Ratios (CRs) up to 10 for a 4-QAM (Quadrature Amplitude Modulation) signal having carrier frequency of 350 MHz and working at a symbol rate of 46 MSym/s.

We showcase the capabilities of V2Verifier, a new open-source software-defined radio (SDR) testbed for vehicle-to-vehicle (V2V) communications security, to expose the strengths and vulnerabilities of current V2V security systems based on the IEEE 1609.2 standard. V2Verifier supports both major V2V technologies and facilitates a broad range of experimentation with upper- and lower-layer attacks using a combination of SDRs and commercial V2V on-board units (OBUs). We demonstrate two separate attacks (jamming and replay) against Dedicated Short Range Communication (DSRC) and Cellular Vehicle-to-Everything (C-V2X) technologies, experimentally quantifying the threat posed by these types of attacks. We also use V2Verifier's open-source implementation to show how the 1609.2 standard can effectively mitigate certain types of attacks (e.g., message replay), facilitating further research into the security of V2V.

Context: The technical debt (TD) metaphor helps to conceptualize the pending issues and trade-offs made during software development. Knowing TD causes can support in defining preventive actions and having information about effects aids in the prioritization of TD payment. Goal: To investigate the impact of the experience level on how practitioners perceive the most likely causes that lead to TD and the effects of TD that have the highest impacts on software projects. Method: We approach this topic by surveying 227 practitioners. Results: While experienced software developers focus on human factors as TD causes and external quality attributes as TD effects, low experienced developers seem to concentrate on technical issues as causes and internal quality issues and increased project effort as effects. Missing any of these types of causes could lead a team to miss the identification of important TD, or miss opportunities to preempt TD. On the other hand, missing important effects could hamper effective planning or erode the effectiveness of decisions about prioritizing TD items. Conclusion: Having software development teams composed of practitioners with a homogeneous experience level can erode the team's ability to effectively manage TD.

This work seeks to advance the state of the art in HPC I/O performance analysis and interpretation. In particular, we demonstrate effective techniques to: (1) model output performance in the presence of I/O interference from production loads; (2) build features from write patterns and key parameters of the system architecture and configurations; (3) employ suitable machine learning algorithms to improve model accuracy. We train models with five popular regression algorithms and conduct experiments on two distinct production HPC platforms. We find that the lasso and random forest models predict output performance with high accuracy on both of the target systems. We also explore use of the models to guide adaptation in I/O middleware systems, and show potential for improvements of at least 15% from model-guided adaptation on 70% of samples, and improvements up to 10 x on some samples for both of the target systems.

PCIe (Peripheral Component Interconnect express) protocol is the de facto protocol to bridge CPU and peripheral devices like GPU, NIC, and SSD drive. There is an increasing demand to install more peripheral devices on a single machine, but the PCIe interfaces offered by Intel CPUs are fixed. To resolve such contention, PCIe switch, PCH (Platform Controller Hub), or virtualization cards are installed on the machine to allow multiple devices to share a PCIe interface. Congestion happens when the collective PCIe traffic from the devices overwhelm the PCIe link capacity, and transmission delay is then introduced.In this work, we found the PCIe delay not only harms device performance but also leaks sensitive information about a user who uses the machine. In particular, as user’s activities might trigger data movement over PCIe (e.g., between CPU and GPU), by measuring PCIe congestion, an adversary accessing another device can infer the victim’s secret indirectly. Therefore, the delay resulted from I/O congestion can be exploited as a side-channel. We demonstrate the threat from PCIe congestion through 2 attack scenarios and 4 victim settings. Specifically, an attacker can learn the workload of a GPU in a remote server by probing a RDMA NIC that shares the same PCIe switch and measuring the delays. Based on the measurement, the attacker is able to know the keystroke timings of the victim, what webpage is rendered on the GPU, and what machine-learning model is running on the GPU. Besides, when the victim is using a low-speed device, e.g., an Ethernet NIC, an attacker controlling an NVMe SSD can launch a similar attack when they share a PCH or virtualization card. The evaluation result shows our attack can achieve high accuracy (e.g., 96.31% accuracy in inferring webpage visited by a victim).

Cloud computing has helped in managing big data and providing resources remotely and ubiquitously, but it has some latency and security concerns. Fog has provided tremendous advantages over cloud computing which include low latency rate, improved real-time interactions, reduced network traffic overcrowding, and improved reliability, however, security concerns need to be addressed separately. Another major issue in the cloud is Cloud Lock-in/Vendor Lock-in. Through this research, an effort has been made to extend fog computing and Searchable Encryption technologies. The proposed system can reduce the issue of cloud lock-in faced in traditional cloud computing. The SE schemes used in this paper are Symmetric Searchable Encryption (SSE) and Multi-keyword Ranked Searchable Encryption (MRSE) to achieve confidentiality, privacy, fine-grained access control, and efficient keyword search. This can help to achieve better access control and keyword search simultaneously. An important use of this technique is it helps to prevent the issue of cloud/vendor lock-in. This can shift some computation and storage of index tables over fog nodes that will reduce the dependency on Cloud Service Providers (CSPs).

Artificial intelligence technology is becoming more active in all areas of our lives day by day. This technology affects our daily life by more developing in areas such as industry 4.0, security and education. Deep reinforcement learning is one of the most developed algorithms in the field of artificial intelligence. In this study, it is aimed that three different robots in a limited area learn to move without hitting each other, fixed obstacles and the boundaries of the field. These robots have been trained using the deep reinforcement learning approach and Proximal policy optimization (PPO) policy. Instead of uses value-based methods with the discrete action space, PPO that can easily manipulate the continuous action field and successfully determine the action of the robots has been proposed. PPO policy achieves successful results in multi-agent problems, especially with the use of the Actor-Critic network. In addition, information is given about environment control and learning approaches for swarm behavior. We propose parameter sharing and behavior-based method for this study. Finally, trained model is recorded and tested in 9 different environments where the obstacles are located differently. With our method, robots can perform their tasks in closed environments in the real world without damaging anyone or anything.

Scientific applications built on wide-area distributed systems such as emerging cloud based architectures and the legacy grid computing infrastructure often struggle with user adoption even though they succeed from a systems research perspective. This paper examines the coupling of user-centered design processes with modern distributed systems. Further in this paper, we describe approaches for conceptualizing a product that solves a recognized need: to develop a data gateway to serve the data management and research needs of experimentalists of electron microscopes and similar shared scientific instruments in the context of a research service laboratory. The purpose of the data gateway is to provide secure, controlled access to data generated from a wide range of scientific instruments. From the functional perspective, we focus on the basic processing of raw data that underlies the lab's "business" processes, the movement of data from the laboratory to central access and archival storage points, and the distribution of data to respective authorized users. Through the gateway interface, users will be able to share the instrument data with collaborators or copy it to remote storage servers. Basic pipelines for extracting additional metadata (through a pluggable parser framework) will be enabled. The core contribution described in this paper, building on the aforementioned distributed data management capabilities, is the adoption of user-centered design processes for developing the scientific user interface. We describe the user-centered design methodology for exploring user needs, iteratively testing the design, learning from user experiences, and adapting what we learn to improve design and capabilities. We further conclude that user-centered design is, in turn, best enabled by an adaptable distributed systems framework. A key challenge to implementing a user-centered design is to have design tools closely linked with a software system architecture that can evolve over time while providing a highly available data gateway. A key contribution of this paper is to share the insights from crafting such an evolvable design-build-evaluate-deploy architecture and plans for iterative development and deployment.

Peer code review has been found to be effective in identifying security vulnerabilities. However, despite practicing mandatory code reviews, many Open Source Software (OSS) projects still encounter a large number of post-release security vulnerabilities, as some security defects escape those. Therefore, a project manager may wonder if there was any weakness or inconsistency during a code review that missed a security vulnerability. Answers to this question may help a manager pinpointing areas of concern and taking measures to improve the effectiveness of his/her project's code reviews in identifying security defects. Therefore, this study aims to identify the factors that differentiate code reviews that successfully identified security defects from those that missed such defects. With this goal, we conduct a case-control study of Chromium OS project. Using multi-stage semi-automated approaches, we build a dataset of 516 code reviews that successfully identified security defects and 374 code reviews where security defects escaped. The results of our empirical study suggest that the are significant differences between the categories of security defects that are identified and that are missed during code reviews. A logistic regression model fitted on our dataset achieved an AUC score of 0.91 and has identified nine code review attributes that influence identifications of security defects. While time to complete a review, the number of mutual reviews between two developers, and if the review is for a bug fix have positive impacts on vulnerability identification, opposite effects are observed from the number of directories under review, the number of total reviews by a developer, and the total number of prior commits for the file under review.

With the rise of the cloud computing and services, the network environments tend to be more complex and enormous. Security control becomes more and more hard due to the frequent and various access and requests. There are a few techniques to solve the problem which developed separately in the recent years. Network Micro-Segmentation provides the system the ability to keep different parts separated. Zero Trust Model ensures the network is access to trusted users and business by applying the policy that verify and authenticate everything. With the combination of Segmentation and Zero Trust Model, a system will obtain the ability to control the access to organizations' or industrial valuable assets. To implement the cooperation, the paper designs a strategy named light verification to help the process to be painless for the cost of inspection. The strategy was found to be effective from the perspective of the technical management, security and usability.

This paper introduces a scheme for achieving trustworthy computing on SoCs that use an outsourced AXI interconnect for on-chip communication. This is achieved through component guarding, data tagging, event verification, and consequently responding dynamically to an attack. Experimental results confirm the ability of the proposed scheme to detect HT attacks and respond to them at run-time. The proposed scheme extends the state-of-art in trustworthy computing on untrustworthy components by focusing on the issue of an untrusted on-chip interconnect for the first time, and by developing a scheme that is independent of untrusted third-party IP.