Biblio

Code authorship identification can assist in identifying creators of malware, identifying plagiarism, and giving insights in copyright infringement cases. Taking inspiration from facial recognition work, we apply recent advances in metric learning to the problem of authorship identification and verification. The metric learning approach makes it possible to measure similarity in the learned embedding space. Access to a discriminative similarity measure allows for the estimation of probability distributions that facilitate open-set classification and verification. We extend our analysis to verification based on sets of files, a previously unexplored problem domain in large-scale author identification. On closed-set tasks we achieve competitive accuracies, but do not improve on the state of the art.

Magnetized Liner Inertial Fusion (MagLIF) is a magneto-inertial fusion concept that relies on fuel magnetization, laser preheat, and a magnetically driven implosion to produce fusion conditions. In MagLIF, the target is a roughly 10 mm long, 5 mm diameter, 0.5 mm thick, cylindrical beryllium shell containing 1 mg/cm 3 D 2 gas. An axial magnetic field on the order of 10 T is applied to the target, and several kJ of laser energy is deposited into the fuel. Up to 20 MA of current is driven axially through the beryllium target, causing it to implode over approximately 100 ns. The implosion produces a 100-μm diameter, 8-mm tall fuel column with a burn-averaged ion temperature of several keV, that generates 10 11 -10 13 DD neutrons.

X-ray radiography has been used to diagnose a wide variety of experiments at the Z facility including inertial confinement fusion capsule implosions, the growth of the magneto-Rayleigh-Taylor instability in solid liners, and the development of helical structures in axially magnetized liner implosions. In these experiments, the Z Beamlet laser (1 kJ, 1 ns) was used to generate the x-ray source. An alternate x-ray source is desirable in experiments where the Z Beamlet laser is used for another purpose (e.g., preheating the fuel in magnetized liner inertial fusion experiments) or when multiple radiographic lines of sight are necessary.

Magnetized Liner Inertial Fusion (MagLIF) is a magneto-inertial fusion (MIF) concept being studied on the Z-machine at Sandia National Laboratories. MagLIF relies on quasi-adiabatic heating of a gaseous deuterium (DD) fuel and flux compression of a background axially oriented magnetic field to achieve fusion relevant plasma conditions. The magnetic flux per fuel radial extent determines the confinement of charged fusion products and is thus of fundamental interest in understanding MagLIF performance. It was recently shown that secondary DT neutron spectra and yields are sensitive to the magnetic field conditions within the fuel, and thus provide a means by which to characterize the magnetic confinement properties of the fuel. 1 , 2 , 3 We utilize an artificial neural network to surrogate the physics model of Refs. [1] , [2] , enabling Bayesian inference of the magnetic confinement parameter for a series of MagLIF experiments that systematically vary the laser preheat energy deposited in the target. This constitutes the first ever systematic experimental study of the magnetic confinement properties as a function of fundamental inputs on any neutron-producing MIF platform. We demonstrate that the fuel magnetization decreases with deposited preheat energy in a fashion consistent with Nernst advection of the magnetic field out of the hot fuel and diffusion into the target liner.

Dealing with algorithms, which process large amount of similar data by using significant number of small and various sizes of memory allocation/de-allocation in a dynamic yet deterministic way, is an important issue for soft real-time systems designs. In order to improve the response time, efficiency and security of this kind of processing, we propose a software-based memory management method based on hierarchy of shared memory pools, which could be used to replace standard heap management mechanism of the operating system for some cases. Implementation of this memory management scheme can allocate memory through processing allocation/de-allocation requests of required space. Lockable implementation of this model can safely deal with the multi-threaded concurrent access. We also provide the results of experiments, according to which response time of test systems with soft time-bounded execution demand were considerably improved.

Traffic Signal Control using Reinforcement Learning has been proved to have potential in alleviating traffic congestion in urban areas. Although research has been conducted in this field, it is still an open challenge to find an effective but low-cost solution to this problem. This paper presents multiple deep reinforcement learning-based traffic signal control systems that can help regulate the flow of traffic at intersections and then compares the results. The proposed systems are coupled with SUMO (Simulation of Urban MObility), an agent-based simulator that provides a realistic environment to explore the outcomes of the models.

System recommendation is currently on the rise: more and more e-commerce rely on this feature to give more privilege to their users. However, system recommendation still faces a lot of problems that can lead to its downfall. For instance, the cold start problem and lack of privacy for user’s data in system recommendation will make the quality of this system lesser than ever. Moreover, e-commerce also faces another significant issue which is the lack of social presence. Compared to offline shopping, online shopping in e-commerce may be seen as lacking human presence and sociability as it is more impersonal, cold, automated, and generally devoid of face-to-face interactions. Hence, all of those issues mentioned above may lead to the regression of user’s trust toward e-commerce itself. This study will focus on solving those problems using conversational design interaction in the form of a Virtual Agent. This Virtual Agent can help e-commerce gather user preferences and give clear and direct information regarding the use of user’s data as well as help the user find products, promo, or similar products that they seek in e-commerce. The final result of this solution is a high fidelity prototype designed using User-Centered Design Methodology and Natural Conversational Framework. The implementation of this solution is carried out in Shopee e-commerce by modifying their product recommendation system. This prototype was measured using the usability testing method for usability goals efficient to use and user experience goals helpful.

In order to solve the problem of data analysis and application caused by the inefficient integration of hardware and software compatibility of hardware in the Internet of things, this paper proposes and designs a C/S framework communication system based on task driven and multi-user authority. By redefining the relationship between users and hardware and adopting the matching framework for different modules, the system realizes the high concurrent and complex data efficient collaborative processing between software and hardware. Finally, by testing and verifying the functions of the system, the communication system effectively realizes the functions of data processing between software and hardware, and achieves the expected results.

In the ever evolving Internet threat landscape, Distributed Denial-of-Service (DDoS) attacks remain a popular means to invoke service disruption. DDoS attacks, however, have evolved to become a tool of deceit, providing a smokescreen or distraction while some other underlying attack takes place, such as data exfiltration. Knowing the intent of a DDoS, and detecting underlying attacks which may be present concurrently with it, is a challenging problem. An entity whose network is under a DDoS attack may not have the support personnel to both actively fight a DDoS and try to mitigate underlying attacks. Therefore, any system that can detect such underlying attacks should do so only with a high degree of confidence. Previous work utilizing flow aggregation techniques with multi-class anomaly detection showed promise in both DDoS detection and detecting underlying attacks ongoing during an active DDoS attack. In this work, we head in the opposite direction, utilizing flow segmentation and concurrent flow feature aggregation, with the primary goal of greatly reduced detection times of both DDoS and underlying attacks. Using the same multi-class anomaly detection approach, we show greatly improved detection times with promising detection performance.

In this work an overview of basic approaches to choosing protective measures for automated process control systems is done. The aim of the research was to develop a method for choosing protection measures for information security at every APCs level using set theory within analysis of basic sets of protection measures. In the framework of the research relevant attacks on industrial infrastructure are considered, an algorithm of choosing APCs protective measures is constructed, and it is suggested that it is required to use protective measures for every system level in accordance with an individual assessment of data protection class at the corresponding level. The authors concluded that it is necessary to exclude from consideration “specification of an adapted basic set” of the algorithm for choosing APCs protection measures in case the adapted basic set of APCs protective measures provides blocking all security threats at the considered system level. The approach to choosing protection measures based on building Euler-Venn diagrams is suggested. The results of the research are recommended to be used when modeling information security threats and developing requirements for APCs information protection means.

In modern power grids (PGs), load frequency control (LFC) is effectively employed to preserve the frequency within the allowable ranges. However, LFC dependence on information and communication technologies (ICTs) makes PGs vulnerable to cyber attacks. Manipulation of measured data and control commands known as false data injection attacks (FDIAs) can negatively affect grid frequency performance and destabilize PG. This paper investigates the frequency performance of an isolated PG under coordinated FDIAs. A control scheme based on the combination of a Kalman filter, a chi-square detector, and a linear quadratic Gaussian controller is proposed to detect and mitigate the coordinated FDIAs. The efficiency of the proposed control scheme is evaluated under two types of scaling and exogenous FDIAs. The simulation results demonstrate that the proposed control scheme has significant capabilities to detect and mitigate the designed FDIAs.

Phasor measurement units (PMUs) are used in power grids across North America to measure the amplitude, phase, and frequency of an alternating voltage or current. PMU's use the IEEE C37.118 protocol to send telemetry to phasor data collectors (PDC) and human machine interface (HMI) workstations in a control center. However, the C37.118 protocol utilizes the internet protocol stack without any authentication mechanism. This means that the protocol is vulnerable to false data injection (FDI) and false command injection (FCI). In order to study different scenarios in which C37.118 protocol's integrity and confidentiality can be compromised, we created a testbed that emulates a C37.118 communication network. In this testbed we conduct FCI and FDI attacks on real-time C37.118 data packets using a packet manipulation tool called Scapy. Using this platform, we generated C37.118 FCI and FDI datasets which are processed by multi-label machine learning classifier algorithms, such as Decision Tree (DT), k-Nearest Neighbor (kNN), and Naive Bayes (NB), to find out how effective machine learning can be at detecting such attacks. Our results show that the DT classifier had the best precision and recall rate.

Power grids are the most extensive man-made systems that are difficult to control and monitor. With the development of conventional power grids and moving toward smart grids, power systems have undergone vast changes since they use the Internet to transmit information and control commands to different parts of the power system. Due to the use of the Internet as a basic infrastructure for smart grids, attackers can sabotage the communication networks and alter the measurements. Due to the complexity of the smart grids, it is difficult for the network operator to detect such cyber-attacks. The attackers can implement the attack in a manner that conventional Bad Data detection (BDD) systems cannot detect since it may not violate the physical laws of the power system. This paper uses the cross wavelet transform (XWT) to detect stealth false data injections attacks (FDIAs) against state estimation (SE) systems. XWT can capture the coherency between measurements of adjacent buses and represent it in time and frequency space. Then, we train a machine learning classification algorithm to distinguish attacked measurements from normal measurements by applying a feature extraction technique.

Ransomware is one of the fastest growing threats to internet security. New Ransomware attacks happen around the globe, on a weekly basis. These attacks happen to individual users and groups, from almost any type of business. Many of these attacks involve Ransomware as a service, where one attacker creates a template Malware, which can be purchased and modified by other attackers to perform specific actions. The District Ransomware was a less well-known strain. This work focuses on statically and dynamically analyzing the District Ransomware and presenting the results.

Mobile antivirus technologies incorporate static analysis which involves the analysis of programs without its execution. This process relies on pattern matching against a signature repository to identify malware, which can be easily tricked by transformation techniques such as obfuscation. Obfuscation as an evasion technique renders character strings disguised and incomprehensive, to prevent tampering and reengineering, which poses to be a valuable technique malware developers adopt to evade detection. This paper attempts to study the detection efficiency of static analyzers against obfuscated Android malware. This study is the first step in a larger project attempting to improve the efficiency of malware detectors.

Recently, Mobile Edge Cloud computing (MEC) has attracted attention both from academia and industry. The idea of moving a part of cloud resources closer to users and data sources can bring many advantages in terms of speed, data traffic, security and context-aware services. The MEC infrastructure does not only host and serves applications next to the end-users, but services can be dynamically migrated and reallocated as mobile users move in order to guarantee latency and performance constraints. This specific requirement calls for the involvement and collaboration of multiple MEC providers, which raises a major issue related to trustworthiness. Two main challenges need to be addressed: i) trustworthiness needs to be handled in a manner that does not affect latency or performance, ii) trustworthiness is considered in different dimensions - not only security metrics but also performance and quality metrics in general. In this paper, we propose a trust layer for public MEC infrastructure that handles establishing and updating trust relations among all MEC entities, making the interaction withing a MEC network transparent. First, we define trust attributes affecting the trusted quality of the entire infrastructure and then a methodology with a computation model that combines these trust attribute values. Our experiments showed that the trust model allows us to reduce latency by removing the burden from a single MEC node, while at the same time increase the network trustworthiness.

Data are the basis in Digital Twin (DT) to set up bidirectional mapping between physical and virtual spaces, and realize critical environmental sensing, decision making and execution. Thus, trustworthiness is a necessity in data content as well as data operations. A dual blockchain framework is proposed to realize comprehensive data security in various DT scenarios. It is highly adaptable, scalable, evolvable, and easy to be integrated into Digital Twin Network (DTN) as enhancement.

Spatial crowdsourcing has stimulated various new applications such as taxi calling and food delivery. A key enabler for these spatial crowdsourcing based applications is to plan routes for crowd workers to execute tasks given diverse requirements of workers and the spatial crowdsourcing platform. Despite extensive studies on task planning in spatial crowdsourcing, few have accounted for the location privacy of tasks, which may be misused by an untrustworthy platform. In this paper, we explore efficient task planning for workers while protecting the locations of tasks. Specifically, we define the Privacy-Preserving Task Planning (PPTP) problem, which aims at both total revenue maximization of the platform and differential privacy of task locations. We first apply the Laplacian mechanism to protect location privacy, and analyze its impact on the total revenue. Then we propose an effective and efficient task planning algorithm for the PPTP problem. Extensive experiments on both synthetic and real datasets validate the advantages of our algorithm in terms of total revenue and time cost.

The burgeoning networked computing devices create many distributed systems and generate new signals on a large scale. Many Internet of Things (IoT) applications, such as peer-to-peer streaming of multimedia data, crowdsourcing, and measurement by sensor networks, can be modeled as a form of big data. Processing massive data calls for new data structures and algorithms different from traditional ones designed for small-scale problems. For measurement from networked distributed systems, we consider an essential data format: signals on graphs. Due to limited computing resources, the sensor nodes in the distributed systems may outsource the computing tasks to third parties, such as cloud platforms, arising a severe concern on data privacy. A de-facto solution is to have third parties only process encrypted data. We propose a novel and efficient privacy-preserving secure outsourced computation protocol for denoising signals on the graph based on the information-theoretic secure multi-party computation (ITS-MPC). Denoising the data makes paths for further meaningful data processing. From experimenting with our algorithms in a testbed, the results indicate a better efficiency of our approach than a counterpart approach with computational security.

Information system security is very important and very complicated, security is to prevent potential crisis. To detect both from external invasion behavior, also want to check the internal unauthorized behavior. Presented here ABHIDS hybrid intrusion detection system model, designed a component Agent, controller, storage, filter, manager component (database), puts forward a new detecting DDoS attacks (trinoo) algorithm and the implementation. ABHIDS adopts object-oriented design method, a study on intrusion detection can be used as a working mechanism of the algorithms and test verification platform.

In the last decade the use of artificial neural networks (ANNs) in many fields like image processing or speech recognition has become a common practice because of their effectiveness to solve complex tasks. However, in such a rush, very little attention has been paid to security aspects. In this work we explore the possibility to embed a watermark into the ANN parameters. We exploit model redundancy and adaptation capacity to lock a subset of its parameters to carry the watermark sequence. The watermark can be extracted in a simple way to claim copyright on models but can be very easily attacked with model fine-tuning. To tackle this culprit we devise a novel watermark aware training strategy. We aim at delving into the loss landscape to find an optimal configuration of the parameters such that we are robust to fine-tuning attacks towards the watermarked parameters. Our experimental results on classical ANN models trained on well-known MNIST and CIFAR-10 datasets show that the proposed approach makes the embedded watermark robust to fine-tuning and compression attacks.

With the development of 5G technology and intelligent terminals, the future direction of the Industrial Internet of Things (IIoT) evolution is Pervasive Edge Computing (PEC). In the pervasive edge computing environment, intelligent terminals can perform calculations and data processing. By migrating part of the original cloud computing model's calculations to intelligent terminals, the intelligent terminal can complete model training without uploading local data to a remote server. Pervasive edge computing solves the problem of data islands and is also successfully applied in scenarios such as vehicle interconnection and video surveillance. However, pervasive edge computing is facing great security problems. Suppose the remote server is honest but curious. In that case, it can still design algorithms for the intelligent terminal to execute and infer sensitive content such as their identity data and private pictures through the information returned by the intelligent terminal. In this paper, we research the problem of honest but curious remote servers infringing intelligent terminal privacy and propose a differential privacy collaborative deep learning algorithm in the pervasive edge computing environment. We use a Gaussian mechanism that meets the differential privacy guarantee to add noise on the first layer of the neural network to protect the data of the intelligent terminal and use analytical moments accountant technology to track the cumulative privacy loss. Experiments show that with the Gaussian mechanism, the training data of intelligent terminals can be protected reduction inaccuracy.

Existing group shilling attack detection methods mainly depend on human feature engineering to extract group attack behavior features, which requires a high knowledge cost. To address this problem, we propose a group shilling attack detection method based on maximum density subtensor mining. First, the rating time series of each item is divided into time windows and the item tensor groups are generated by establishing the user-rating-time window data models of three-dimensional tensor. Second, the M-Zoom model is applied to mine the maximum dense subtensor of each item, and the subtensor groups with high consistency of behaviors are selected as candidate groups. Finally, a dual-input convolutional neural network model is designed to automatically extract features for the classification of real users and group attack users. The experimental results on the Amazon and Netflix datasets show the effectiveness of the proposed method.

Recommender systems have been proved to be effective techniques to provide users with better experiences. However, when a recommender knows the user's preference characteristics or gets their sensitive information, then a series of privacy concerns are raised. A amount of solutions in the literature have been proposed to enhance privacy protection degree of recommender systems. Although the existing solutions have enhanced the protection, they led to a decrease in recommendation accuracy simultaneously. In this paper, we propose a security-aware hybrid recommendation method by combining the factorization and regression techniques. Specifically, the differential privacy mechanism is integrated into data pre-processing for data encryption. Firstly data are perturbed to satisfy differential privacy and transported to the recommender. Then the recommender calculates the aggregated data. However, applying differential privacy raises utility issues of low recommendation accuracy, meanwhile the use of a single model may cause overfitting. In order to tackle this challenge, we adopt a fusion prediction model by combining linear regression (LR) and matrix factorization (MF) for collaborative recommendation. With the MovieLens dataset, we evaluate the recommendation accuracy and regression of our recommender system and demonstrate that our system performs better than the existing recommender system under privacy requirement.

In a group shilling attack, attackers work collaboratively to inject fake profiles aiming to obtain desired recommendation result. This type of attacks is more harmful to recommender systems than individual shilling attacks. Previous studies pay much attention to detect individual attackers, and little work has been done on the detection of shilling groups. In this work, we introduce a topic modeling method of natural language processing into shilling attack detection and propose a shilling group detection method on the basis of hierarchical topic model. First, we model the given dataset to a series of user rating documents and use the hierarchical topic model to learn the specific topic distributions of each user from these rating documents to describe user rating behaviors. Second, we divide candidate groups based on rating value and rating time which are not involved in the hierarchical topic model. Lastly, we calculate group suspicious degrees in accordance with several indicators calculated through the analysis of user rating distributions, and use the k-means clustering algorithm to distinguish shilling groups. The experimental results on the Netflix and Amazon datasets show that the proposed approach performs better than baseline methods.