Biblio

Mortality from lung cancer has ranked high among cancers for many years. Early detection of lung cancer is critical for disease prevention, cure, and mortality rate reduction. Many existing detection methods on lung nodules can achieve high sensitivity but meanwhile introduce an excessive number of false-positive proposals, which is clinically unpractical. In this paper, we propose the multi-head detection and spatial attention network, shortly MHSnet, to address this crucial false-positive issue. Specifically, we first introduce multi-head detectors and skip connections to capture multi-scale features so as to customize for the variety of nodules in sizes, shapes, and types. Then, inspired by how experienced clinicians screen CT images, we implemented a spatial attention module to enable the network to focus on different regions, which can successfully distinguish nodules from noisy tissues. Finally, we designed a lightweight but effective false-positive reduction module to cut down the number of false-positive proposals, without any constraints on the front network. Compared with the state-of-the-art models, our extensive experimental results show the superiority of this MHSnet not only in the average FROC but also in the false discovery rate (2.64% improvement for the average FROC, 6.39% decrease for the false discovery rate). The false-positive reduction module takes a further step to decrease the false discovery rate by 14.29%, indicating its very promising utility of reducing distracted proposals for the downstream tasks relied on detection results.

Internet of Things (IoT) is widely present nowadays, from businesses to connected houses, and more. IoT is considered a part of the Internet of the future and will comprise billions of intelligent communication. These devices transmit data from sensors to entities like servers to perform suitable responses. The problem of securing these data from cyberattacks increases due to the sensitive information it contains. In addition, studies have shown that most of the time data transiting in IoT devices does not apply encrypted communication. Thus, anyone has the ability to listen to or modify the information. Encrypting communications seems mandatory to secure networks and data transiting from sensors to servers. In this paper, we propose an approach to secure the transmission and the storage of data in IoT using Elliptic Curve Cryptography (ECC). The proposed method offers a high level of security at a reasonable computational cost. Indeed, we present an adequate architecture that ensures the use of a state-of-the-art cryptography algorithm to encrypt sensitive data in IoT.

Differential privacy mechanisms have been proposed to guarantee the privacy of individuals in various types of statistical information. When constructing a probabilistic mechanism to satisfy differential privacy, it is necessary to consider the impact of an arbitrary record on its statistics, i.e., sensitivity, but there are situations where sensitivity is difficult to derive. In this paper, we first summarize the situations in which it is difficult to derive sensitivity in general, and then propose a definition equivalent to the conventional definition of differential privacy to deal with them. This definition considers neighboring datasets as in the conventional definition. Therefore, known differential privacy mechanisms can be applied. Next, as an example of the difficulty in deriving sensitivity, we focus on the t-test, a basic tool in statistical analysis, and show that a concrete differential privacy mechanism can be constructed in practice. Our proposed definition can be treated in the same way as the conventional differential privacy definition, and can be applied to cases where it is difficult to derive sensitivity.

Personal data privacy is a great concern by governments across the world as citizens generate huge amount of data continuously and industries using this for betterment of user centric services. There must be a reasonable balance between data privacy and utility of data. Differential privacy is a promise by data collector to the customer’s personal privacy. Centralised Differential Privacy (CDP) is performing output perturbation of user’s data by applying required privacy budget. This promises the inclusion or exclusion of individual’s data in data set not going to create significant change for a statistical query output and it offers -Differential privacy guarantee. CDP is holding a strong belief on trusted data collector and applying global sensitivity of the data. Local Differential Privacy (LDP) helps user to locally perturb his data and there by guaranteeing privacy even with untrusted data collector. Many differential privacy algorithms handles parameters like privacy budget, sensitivity and data utility in different ways and mostly trying to keep trade-off between privacy and utility of data. This paper evaluates differential privacy algorithms in regard to the privacy support it offers according to the sensitivity of the data. Generalized application of privacy budget is found ineffective in comparison to the sensitivity based usage of privacy budget.

Current intrusion detection techniques cannot keep up with the increasing amount and complexity of cyber attacks. In fact, most of the traffic is encrypted and does not allow to apply deep packet inspection approaches. In recent years, Machine Learning techniques have been proposed for post-mortem detection of network attacks, and many datasets have been shared by research groups and organizations for training and validation. Differently from the vast related literature, in this paper we propose an early classification approach conducted on CSE-CIC-IDS2018 dataset, which contains both benign and malicious traffic, for the detection of malicious attacks before they could damage an organization. To this aim, we investigated a different set of features, and the sensitivity of performance of five classification algorithms to the number of observed packets. Results show that ML approaches relying on ten packets provide satisfactory results.

Machine learning (ML) models are increasingly being used in the development of Malware Detection Systems. Existing research in this area primarily focuses on developing new architectures and feature representation techniques to improve the accuracy of the model. However, recent studies have shown that existing state-of-the art techniques are vulnerable to adversarial machine learning (AML) attacks. Among those, data poisoning attacks have been identified as a top concern for ML practitioners. A recent study on clean-label poisoning attacks in which an adversary intentionally crafts training samples in order for the model to learn a backdoor watermark was shown to degrade the performance of state-of-the-art classifiers. Defenses against such poisoning attacks have been largely under-explored. We investigate a recently proposed clean-label poisoning attack and leverage an ensemble-based Nested Training technique to remove most of the poisoned samples from a poisoned training dataset. Our technique leverages the relatively large sensitivity of poisoned samples to feature noise that disproportionately affects the accuracy of a backdoored model. In particular, we show that for two state-of-the art architectures trained on the EMBER dataset affected by the clean-label attack, the Nested Training approach improves the accuracy of backdoor malware samples from 3.42% to 93.2%. We also show that samples produced by the clean-label attack often successfully evade malware classification even when the classifier is not poisoned during training. However, even in such scenarios, our Nested Training technique can mitigate the effect of such clean-label-based evasion attacks by recovering the model's accuracy of malware detection from 3.57% to 93.2%.

Communication systems across a variety of applications are increasingly using the angular domain to improve spectrum management. They require new sensing architectures to perform energy-efficient measurements of the electromagnetic environment that can be deployed in a variety of use cases. This paper presents the Directional Spectrum Sensor (DSS), a compressive sampling (CS) based analog-to-information converter (CS-AIC) that performs spectrum scanning in a focused beam. The DSS offers increased spectrum sensing sensitivity and interferer tolerance compared to omnidirectional sensors. The DSS implementation uses a multi-antenna beamforming architecture with local oscillators that are modulated with pseudo random waveforms to obtain CS measurements. The overall operation, limitations, and the influence of wideband angular effects on the spectrum scanning performance are discussed. Measurements on an experimental prototype are presented and highlight improvements over single antenna, omnidirectional sensing systems.

Vulnerability detection has always been an essential part of maintaining information security, and the existing work can significantly improve the performance of vulnerability detection. However, due to the differences in representation forms and deep learning models, various methods still have some limitations. In order to overcome this defect, We propose a vulnerability detection method VDBWGDL, based on weight graphs and deep learning. Firstly, it accurately locates vulnerability-sensitive keywords and generates variant codes that satisfy vulnerability trigger logic and programmer programming style through code variant methods. Then, the control flow graph is sliced for vulnerable code keywords and program critical statements. The code block is converted into a vector containing rich semantic information and input into the weight map through the deep learning model. According to specific rules, different weights are set for each node. Finally, the similarity is obtained through the similarity comparison algorithm, and the suspected vulnerability is output according to different thresholds. VDBWGDL improves the accuracy and F1 value by 3.98% and 4.85% compared with four state-of-the-art models. The experimental results prove the effectiveness of VDBWGDL.

With the rapid development of information technology, hacker invasion, Internet fraud and privacy disclosure and other events frequently occur, therefore information security issues become the focus of attention. Protecting the secure transmission of information has become a hot topic in today's research. As the carrier of information, image has the characteristics of vivid image and large amount of information. It has become an indispensable part of people's communication. In this paper, we proposed the key simulation analysis research based on M-J set. The research uses a complex iterative mapping to construct M set. On the basis of the constructed M set, the constructed Julia set is used to form the encryption key. The experimental results show that the generalized M-set has the characteristics of chaotic characteristic and initial value sensitivity, and the complex mapping greatly exaggerates the key space. The research on the key space based on the generalized M-J set is helpful to improve the effect of image encryption.

In this study, the parameters of the Jiles-Atherton (JA) model are investigated to determine suitable solution candidates for hysteresis models of a piezoelectric actuator (PEA). The methodology of this study is to perform Monte Carlo experiments on the JA model by randomly selecting parameters that generate hysteresis curves. The solution space is then restrained such that their normalized area and remnant displacements are comparable to those of the PEA. The data resulting from these Monte Carlo simulations show trends in the parameter space that can be used to further restrain parameter selection windows to find suitable JA parameters to model PEAs. In particular, the results show that selection of the reversibility coefficient and the pinning factor strongly affect both of the hysteresis characteristics studied. A large density of solutions is found in certain parameter distributions for both the area and the remnant displacement, but the remnant displacement generates the densest distributions. These results can be used to more effectively find suitable hysteresis models for modeling purposes.

Ubiquitous environment embedded with artificial intelligent consist of heterogenous smart devices communicating each other in several context for the computation of requirements. In such environment the trust among the smart users have taken as the challenge to provide the secure environment during the communication in the ubiquitous region. To provide the secure trusted environment for the users of ubiquitous system proposed approach aims to extract behavior of smart invisible entities by retrieving their behavior of communication in the network and applying the recommendation-based filters using Deep learning (RBF-DL). The proposed model adopts deep learning-based classifier to classify the unfair recommendation with fair ones to have a trustworthy ubiquitous system. The capability of proposed model is analyzed and validated by considering different attacks and additional feature of instances in comparison with generic recommendation systems.

This paper describes a cybersecurity model for Supervisory Control and Data Acquisition system (SCADA) using techniques similar to those used in reliability systems modelling. Previously, cybersecurity events were considered a part of the reliability events of a cyber physical system [1] [2]. Our approach identifies and treats such events separately as unique class of events by itself. Our analyses shows that the hierarchical model described below has the potential for quantifying the cybersecurity posture of a SCADA system, which goes beyond the usual pass/fail metrics that are currently in use [3]. A range of Mean Time to Security Failure (MTTSF) values as shown in the sensitivity studies below can capture both peacetime and wartime cyber risk assessment of the system. While the Attack and Countermeasure Tree (ACT) constructed below could be taken as somewhat simplistic, more detailed security events can be readily introduced to the ACT tree to reflect a better depiction of a cyberattack. For example, the Common Processing Systems (CPS) systems themselves can be further resolved into constituent components that are vulnerable to cyberattacks. Separate models can also be developed for each of the individual failure events, i.e. confidentiality, integrity, and availability, instead of combining them into one failure event as done below. The methodology for computing the MTTSF metric can be extended to other similar cybersecurity metrics, such as those formulated by the Center for Internet Security (CIS) [3], e.g. mean time to restore to operational status, etc. Additional improvements to the model can be obtained with the incorporation of the repair and restore portion of the semi-Markov chain in Figure 3, which will likely require the use of more advance modeling packages.

Active consumers have now been empowered thanks to the smart grid concept. To avoid fossil fuels, the demand side must provide flexibility through Demand Response events. However, selecting the proper participants for an event can be complex due to response uncertainty. The authors design a Contextual Consumer Rate to identify the trustworthy participants according to previous performances. In the present case study, the authors address the problem of new players with no information. In this way, two different methods were compared to predict their rate. Besides, the authors also refer to the consumer privacy testing of the dataset with and without information that could lead to the participant identification. The results found to prove that, for the proposed methodology, private information does not have a high impact to attribute a rate.

Current sensors are widely used in power grid for power metering, automation and power equipment monitoring. Since the tradeoff between the sensitivity and the measurement range needs to be made to design a current sensor, it is difficult to deploy one sensor to measure both the small-magnitude and the large-magnitude current. In this research, we design a surface-mount current sensor by using the tunneling magneto-resistance (TMR) devices and show that the tradeoff between the sensitivity and the detection range can be broken. Two TMR devices of different sensitivity degrees were integrated into one current sensor module, and a signal processing algorithm was implemented to fusion the outputs of the two TMR devices. Then, a platform was setup to test the performance of the surface-mount current sensor. The results showed that the designed current sensor could measure the current from 2 mA to 100 A with an approximate 93 dB dynamic range. Besides, the nonintrusive feature of the surface-mount current sensor could make it convenient to be deployed on-site.

Any type of engineered design requires metrics for trading off both desirable and undesirable properties. For integrated circuits, typical properties include circuit size, performance, power, etc., where for example, performance is a desirable property and power consumption is not. Security metrics, on the other hand, are extremely difficult to develop because there are active adversaries that intend to compromise the protected circuitry. This implies metric values may not be static quantities, but instead are measures that degrade depending on attack effectiveness. In order to deal with this dynamic aspect of a security metric, a general attack model is proposed that enables the effectiveness of various security approaches to be directly compared in the context of an attack. Here, we describe, define and demonstrate that the metrics presented are both meaningful and measurable.

This paper belongs to a sequence of manuscripts that discuss generic and easy-to-apply security metrics for Strong PUFs. These metrics cannot and shall not fully replace in-depth machine learning (ML) studies in the security assessment of Strong PUF candidates. But they can complement the latter, serve in initial PUF complexity analyses, and are much easier and more efficient to apply: They do not require detailed knowledge of various ML methods, substantial computation times, or the availability of an internal parametric model of the studied PUF. Our metrics also can be standardized particularly easily. This avoids the sometimes inconclusive or contradictory findings of existing ML-based security test, which may result from the usage of different or non-optimized ML algorithms and hyperparameters, differing hardware resources, or varying numbers of challenge-response pairs in the training phase.This first manuscript within the abovementioned sequence treats one of the conceptually most straightforward security metrics on that path: It investigates the effects that small perturbations in the PUF-challenges have on the resulting PUF-responses. We first develop and implement several sub-metrics that realize this approach in practice. We then empirically show that these metrics have surprising predictive power, and compare our obtained test scores with the known real-world security of several popular Strong PUF designs. The latter include (XOR) Arbiter PUFs, Feed-Forward Arbiter PUFs, and (XOR) Bistable Ring PUFs. Along the way, our manuscript also suggests techniques for representing the results of our metrics graphically, and for interpreting them in a meaningful manner.

Intrusion Detection System (IDS) is one of the applications to detect intrusions in the network. IDS aims to detect any malicious activities that protect the computer networks from unknown persons or users called attackers. Network security is one of the significant tasks that should provide secure data transfer. Virtualization of networks becomes more complex for IoT technology. Deep Learning (DL) is most widely used by many networks to detect the complex patterns. This is very suitable approaches for detecting the malicious nodes or attacks. Software-Defined Network (SDN) is the default virtualization computer network. Attackers are developing new technology to attack the networks. Many authors are trying to develop new technologies to attack the networks. To overcome these attacks new protocols are required to prevent these attacks. In this paper, a unique deep intrusion detection approach (UDIDA) is developed to detect the attacks in SDN. Performance shows that the proposed approach is achieved more accuracy than existing approaches.

The rapid growth of number of devices that are connected to internet of things (IoT) networks, increases the severity of security problems that need to be solved in order to provide safe environment for network data exchange. The discovery of new vulnerabilities is everyday challenge for security experts and many novel methods for detection and prevention of intrusions are being developed for dealing with this issue. To overcome these shortcomings, artificial intelligence (AI) can be used in development of advanced intrusion detection systems (IDS). This allows such system to adapt to emerging threats, react in real-time and adjust its behavior based on previous experiences. On the other hand, the traffic classification task becomes more difficult because of the large amount of data generated by network systems and high processing demands. For this reason, feature selection (FS) process is applied to reduce data complexity by removing less relevant data for the active classification task and therefore improving algorithm's accuracy. In this work, hybrid version of recently proposed sand cat swarm optimizer algorithm is proposed for feature selection with the goal of increasing performance of extreme learning machine classifier. The performance improvements are demonstrated by validating the proposed method on two well-known datasets - UNSW-NB15 and CICIDS-2017, and comparing the results with those reported for other cutting-edge algorithms that are dealing with the same problems and work in a similar configuration.

Wrist-worn devices enable access to essential information and they are suitable for a wide range of applications, such as gesture and activity recognition. Wrist-worn devices require appropriate technologies when used in sensitive areas, overcoming vulnerabilities in regard to security and privacy. In this work, we propose an approach to recognize wrist rotation by utilizing Visible Light Communication (VLC) that is enabled by low-cost LEDs in an indoor environment. In this regard, we address the channel model of a VLC communicating wristband (VLCcw) in terms of the following factors. The directionality and the spectral composition of the light and the corresponding spectral sensitivity and the directional characteristics of the utilized photodiode (PD). We verify our VLCcw from the simulation environment by a small-scale experimental setup. Then, we analyze the system when white and RGBW LEDs are used. In addition, we optimized the VLCcw system by adding more receivers for the purpose of reducing the number of LEDs on VLCcw. Our results show that the proposed approach generates a feasible real-world simulation environment.

The Inertial Navigation System(INS) and Doppler Velocity Logs(DVL) which are used frequently on autonomous underwater vehicles can be fused under different types of integration architectures. These architectures differ in terms of algorithm requirements and complexity. DVL may experience acoustic beam losses during operation due to environmental factors and abilities of the sensor. In these situations, radial velocity information cannot be received from lost acoustic beam. In this paper, the performances of INS and DVL integration under tightly and loosely coupled architectures are comparatively presented with simulations. In the tightly coupled approach, navigation filter is updated with solely available beam measurements by using sequential measurement update method, and the sensitivity of this method is investigated for acoustic beam losses.

Over past years, the high demand to efficiently process deep learning (DL) models has driven the market of the chip design companies. However, the new Deep Chip architectures, a common term to refer to DL hardware accelerator, have slightly paid attention to the security requirements in quantized neural networks (QNNs), while the black/white -box adversarial attacks can jeopardize the integrity of the inference accelerator. Therefore in this paper, a comprehensive study of the resiliency of QNN topologies to black-box attacks is examined. Herein, different attack scenarios are performed on an FPGA-processor co-design, and the collected results are extensively analyzed to give an estimation of the impact’s degree of different types of attacks on the QNN topology. To be specific, we evaluated the sensitivity of the QNN accelerator to a range number of bit-flip attacks (BFAs) that might occur in the operational lifetime of the device. The BFAs are injected at uniformly distributed times either across the entire QNN or per individual layer during the image classification. The acquired results are utilized to build the entropy-based model that can be leveraged to construct resilient QNN architectures to bit-flip attacks.

Quantized deep neural networks (QDNNs) are necessary for low-power, high throughput, and embedded applications. Previous studies mostly focused on developing optimization methods for the quantization of given models. However, quantization sensitivity depends on the model architecture. Also, the characteristics of weight and activation quantization are quite different. This study proposes a holistic approach for the optimization of QDNNs, which contains QDNN training methods as well as quantization-friendly architecture design. Synthesized data is used to visualize the effects of weight and activation quantization. The results indicate that deeper models are more prone to activation quantization, while wider models improve the resiliency to both weight and activation quantization.

Mobile Edge Computing may become a prevalent platform to support applications where mobile devices have limited compute, storage, energy and/or data privacy concerns. In this paper, we study the efficient provisioning and management of compute resources in the Edge-to-Cloud continuum for different types of real-time applications with timeliness requirements depending on application-level update rates and communication/compute delays. We begin by introducing a highly stylized network model allowing us to study the salient features of this problem including its sensitivity to compute vs. communication costs, application requirements, and traffic load variability. We then propose an online decentralized service placement algorithm, based on estimating network delays and adapting application update rates, which achieves high service availability. Our results exhibit how placement can be optimized and how a load-balancing strategy can achieve near-optimal service availability in large networks.

Physical unclonable functions (PUFs) are used to create unique device identifiers from their inherent fabrication variability. Unstable readings and variation of the PUF response over time are key issues that limit the applicability of PUFs in real-world systems. In this project, we developed a fuzzy extractor (FE) to generate robust cryptographic keys from ReRAM-based PUFs. We tested the efficiency of the proposed FE using BCH and Polar error correction codes. We use ReRAM-based PUFs operating in pre-forming range to generate binary cryptographic keys at ultra-low power with an objective of tamper sensitivity. We investigate the performance of the proposed FE with real data using the reading of the resistance of pre-formed ReRAM cells under various noise conditions. The results show a bit error rate (BER) in the range of 10−5 for the Polar-codes based method when 10% of the ReRAM cell array is erroneous at Signal to Noise Ratio (SNR) of 20dB.This error rate is achieved by using helper data length of 512 bits for a 256 bit cryptographic key. Our method uses a 2:1 ratio for helper data and key, much lower than the majority of previously reported methods. This property makes our method more robust against helper data attacks.

Pooling together samples and testing the resulting mixture is gaining considerable interest as a potential method to markedly increase the rate of testing for SARS-CoV-2, given the resource limited conditions. Such pooling can also be employed for carrying out large scale diagnostic testing of other infectious diseases, especially when the available resources are limited. Therefore, it has become important to design a user-friendly tool to assist clinicians and policy makers, to determine optimal testing pool and sub-pool sizes for their specific scenarios. We have developed such a tool; the calculator web application is available at https://riteshsingh.github.io/poolsize/. The algorithms employed are described and analyzed in this paper, and their application to other scientific fields is also discussed. We find that pooling always reduces the expected number of tests in all the conditions, at the cost of test sensitivity. The No sub-pooling optimal pool size calculator will be the most widely applicable one, because limitations of sample quantity will restrict sub-pooling in most conditions.