Biblio

In the past decades, learning an effective distance metric between pairs of instances has played an important role in the classification and retrieval task, for example, the person identification or malware retrieval in the IoT service. The core motivation of recent efforts focus on improving the metric forms, and already showed promising results on the various applications. However, such models often fail to produce a reliable metric on the ambiguous test set. It happens mainly due to the sampling process of the training set, which is not representative of the distribution of the negative samples, especially the examples that are closer to the boundary of different categories (also called hard negative samples). In this paper, we focus on addressing such problems and propose an adaptive margin deep adversarial metric learning (AMDAML) framework. It exploits numerous common negative samples to generate potential hard (adversarial) negatives and applies them to facilitate robust metric learning. Apart from the previous approaches that typically depend on the search or data augmentation to find hard negative samples, the generation of adversarial negative instances could avoid the limitation of domain knowledge and constraint pairs' amount. Specifically, in order to prevent over fitting or underfitting during the training step, we propose an adaptive margin loss that preserves a flexible margin between the negative (include the adversarial and original) and positive samples. We simultaneously train both the adversarial negative generator and conventional metric objective in an adversarial manner and learn the feature representations that are more precise and robust. The experimental results on practical data sets clearly demonstrate the superiority of AMDAML to representative state-of-the-art metric learning models.

Construction of the audit internal control system based on the online big data mining and decentralized model is done in this paper. How to integrate the novel technologies to internal control is the attracting task. IT audit is built on the information system and is independent of the information system itself. Application of the IT audit in enterprises can provide a guarantee for the security of the information system that can give an objective evaluation of the investment. This paper integrates the online big data mining and decentralized model to construct an efficient system. Association discovery is also called a data link. It uses similarity functions, such as the Euclidean distance, edit distance, cosine distance, Jeckard function, etc., to establish association relationships between data entities. These parameters are considered for comprehensive analysis.

Insider attacks is a well-known problem acknowledged as a threat as early as 1980s. The threat is attributed to legitimate users who take advantage of familiarity with the computational environment and abuse their privileges, can easily cause significant damage or losses. In this paper, we present an active defense model and framework of insider threat detection and sense. Firstly, we describe the hierarchical framework which deal with insider threat from several aspects, and subsequently, show a hierarchy-mapping based insider threats model, the kernel of the threats detection, sense and prediction. The experiments show that the model and framework could sense the insider threat in real-time effectively.

The disadvantages and inextensibility of the traditional network require more novel thoughts for the future network architecture, as for ICN (Information-Centric Network), is an information centered and self-caching network, ICN is deeply rooted in the 5G era, of which concept is user-centered and content-centered. Although the ICN enables cache replacement of content, an information distribution scheduling algorithm is still needed to allocate resources properly due to its limited cache capacity. This paper starts with data popularity, information epilepsy and other data related attributes in the ICN environment. Then it analyzes the factors affecting the cache, proposes the concept and calculation method of Gene value. Since the ICN is still in a theoretical state, this paper describes an ICN scenario that is close to the reality and processes a greedy caching algorithm named GDGCA (Gene Driven Greedy Caching Algorithm). The GDGCA tries to design an optimal simulation model, which based on the thoughts of throughput balance and satisfaction degree (SSD), then compares with the regular distributed scheduling algorithm in related research fields, such as the QoE indexes and satisfaction degree under different Poisson data volumes and cycles, the final simulation results prove that GDGCA has better performance in cache scheduling of ICN edge router, especially with the aid of Information Gene value.

To ensure quality of service and user experience, large Internet companies often monitor various Key Performance Indicators (KPIs) of their systems so that they can detect anomalies and identify failure in real time. However, due to a large number of various KPIs and the lack of high-quality labels, existing KPI anomaly detection approaches either perform well only on certain types of KPIs or consume excessive resources. Therefore, to realize generic and practical KPI anomaly detection in the real world, we propose a KPI anomaly detection framework named iRRCF-Active, which contains an unsupervised and white-box anomaly detector based on Robust Random Cut Forest (RRCF), and an active learning component. Specifically, we novelly propose an improved RRCF (iRRCF) algorithm to overcome the drawbacks of applying original RRCF in KPI anomaly detection. Besides, we also incorporate the idea of active learning to make our model benefit from high-quality labels given by experienced operators. We conduct extensive experiments on a large-scale public dataset and a private dataset collected from a large commercial bank. The experimental resulta demonstrate that iRRCF-Active performs better than existing traditional statistical methods, unsupervised learning methods and supervised learning methods. Besides, each component in iRRCF-Active has also been demonstrated to be effective and indispensable.

Due to the harsh environment and energy limitation, maintaining efficient communication is crucial to the lifetime of Underwater Sensor Networks (UWSN). Named Data Networking (NDN), one of future network architectures, begins to be applied to UWSN. Although Underwater Named Data Networking (UNDN) performs well in data transmission, it still faces some security threats, such as the Denial-of-Service (DoS) attacks caused by Interest Flooding Attacks (IFAs). In this paper, we present a new type of DoS attacks, named as Synergetic Denial-of-Service (SDoS). Attackers synergize with each other, taking turns to reply to malicious interests as late as possible. SDoS attacks will damage the Pending Interest Table, Content Store, and Forwarding Information Base in routers with high concealment. Simulation results demonstrate that the SDoS attacks quadruple the increased network traffic compared with normal IFAs and the existing IFA detection algorithm in UNDN is completely invalid to SDoS attacks. In addition, we analyze the infection problem in UNDN and propose a defense method Trident based on carefully designed adaptive threshold, burst traffic detection, and attacker identification. Experiment results illustrate that Trident can effectively detect and resist both SDoS attacks and normal IFAs. Meanwhile, Trident can robustly undertake burst traffic and congestion.

IoT devices such as Google Home and Amazon Echo provide great convenience to our lives. Many of these IoT devices collect data including Personal Identifiable Information such as names, phone numbers, and addresses and thus IoT security is important. However, conducting security analysis on IoT devices is challenging due to the variety, the volume of the devices, and the special skills required for hardware and software analysis. In this research, we create and demonstrate a dynamic analysis security testing infrastructure for capturing network traffic from IoT devices. The network traffic is automatically mirrored to a server for live traffic monitoring and offline data analysis. Using the dynamic analysis security testing infrastructure, we conduct extensive security analysis on network traffic from Google Home and Amazon Echo. Our testing results indicate that Google Home enforces tighter security controls than Amazon Echo while both Google and Amazon devices provide the desired security level to protect user data in general. The dynamic analysis security testing infrastructure presented in the paper can be utilized to conduct similar security analysis on any IoT devices.

The PyPI ecosystem has indexed millions of Python libraries to allow developers to automatically download and install dependencies of their projects based on the specified version constraints. Despite the convenience brought by automation, version constraints in Python projects can easily conflict, resulting in build failures. We refer to such conflicts as Dependency Conflict (DC) issues. Although DC issues are common in Python projects, developers lack tool support to gain a comprehensive knowledge for diagnosing the root causes of these issues. In this paper, we conducted an empirical study on 235 real-world DC issues. We studied the manifestation patterns and fixing strategies of these issues and found several key factors that can lead to DC issues and their regressions. Based on our findings, we designed and implemented Watchman, a technique to continuously monitor dependency conflicts for the PyPI ecosystem. In our evaluation, Watchman analyzed PyPI snapshots between 11 Jul 2019 and 16 Aug 2019, and found 117 potential DC issues. We reported these issues to the developers of the corresponding projects. So far, 63 issues have been confirmed, 38 of which have been quickly fixed by applying our suggested patches.

Universal style transfer methods typically leverage rich representations from deep Convolutional Neural Network (CNN) models (e.g., VGG-19) pre-trained on large collections of images. Despite the effectiveness, its application is heavily constrained by the large model size to handle ultra-resolution images given limited memory. In this work, we present a new knowledge distillation method (named Collaborative Distillation) for encoder-decoder based neural style transfer to reduce the convolutional filters. The main idea is underpinned by a finding that the encoder-decoder pairs construct an exclusive collaborative relationship, which is regarded as a new kind of knowledge for style transfer models. Moreover, to overcome the feature size mismatch when applying collaborative distillation, a linear embedding loss is introduced to drive the student network to learn a linear embedding of the teacher's features. Extensive experiments show the effectiveness of our method when applied to different universal style transfer approaches (WCT and AdaIN), even if the model size is reduced by 15.5 times. Especially, on WCT with the compressed models, we achieve ultra-resolution (over 40 megapixels) universal style transfer on a 12GB GPU for the first time. Further experiments on optimization-based stylization scheme show the generality of our algorithm on different stylization paradigms. Our code and trained models are available at https://github.com/mingsun-tse/collaborative-distillation.

With the development of deep neural networks, digital fake paintings can be generated by various style transfer algorithms. To detect the fake generated paintings, we analyze the fake generated and real paintings in Fourier frequency domain and observe statistical differences and artifacts. Based on our observations, we propose Fake Generated Painting Detection via Frequency Analysis (FGPD-FA) by extracting three types of features in frequency domain. Besides, we also propose a digital fake painting detection database for assessing the proposed method. Experimental results demonstrate the excellence of the proposed method in different testing conditions.

Despite the high performance of neural style transfer on stylized pictures, we found that Gatys et al [1] algorithm cannot perfectly reconstruct texture style. Output stylized picture could emerge unsatisfied unexpected textures such like muddiness in local area and insufficient grain expression. Our method bases on original algorithm, adding the Gradient Gram description on style loss, aiming to strengthen texture expression and eliminate muddiness. To some extent our method lengthens the runtime, however, its output stylized pictures get higher performance on texture details, especially in the elimination of muddiness.

The development of mobile internet has brought convenience to people, but the openness and diversity of mobile Internet make it face the security threat of communication privacy data disclosure. In this paper, a trusted android device security communication method based on TrustZone is proposed. Firstly, Elliptic Curve Diffie-Hellman (ECDH) key agreement algorithm is used to make both parties negotiate the session key in the Trusted Execution Environment (TEE), and then, we stored the key safely in the TEE. Finally, TEE completes the encryption and decryption of the transmitted data. This paper constructs a secure communication between mobile devices without a trusted third party and analyzes the feasibility of the method from time efficiency and security. The experimental results show that the method can resist malicious application monitoring in the process of data encryption and ensures the security of the session key. Compared with the traditional scheme, it is found that the performance of the scheme is not significantly reduced.

Traditional encryption algorithms are not suitable for modern mass speech situations, while some low-dimensional chaotic encryption algorithms are simple and easy to implement, but their key space often small, leading to poor security, so there is still a lot of room for improvement. Aiming at these problems, this paper proposes a new type of four-dimensional chaotic system and applies it to speech encryption. Simulation results show that the encryption scheme in this paper has higher key space and security, which can achieve the speech encryption goal.

Wireless networking opens up many opportunities to facilitate miniaturized robots in collaborative tasks, while the openness of wireless medium exposes robots to the threats of Sybil attackers, who can break the fundamental trust assumption in robotic collaboration by forging a large number of fictitious robots. Recent advances advocate the adoption of bulky multi-antenna systems to passively obtain fine-grained physical layer signatures, rendering them unaffordable to miniaturized robots. To overcome this conundrum, this paper presents ScatterID, a lightweight system that attaches featherlight and batteryless backscatter tags to single-antenna robots to defend against Sybil attacks. Instead of passively "observing" signatures, ScatterID actively "manipulates" multipath propagation by using backscatter tags to intentionally create rich multipath features obtainable to a single-antenna robot. These features are used to construct a distinct profile to detect the real signal source, even when the attacker is mobile and power-scaling. We implement ScatterID on the iRobot Create platform and evaluate it in typical indoor and outdoor environments. The experimental results show that our system achieves a high AUROC of 0.988 and an overall accuracy of 96.4% for identity verification.

Cloud Native, the emerging computing infrastructure has become a new trend for cloud computing, especially after the development of containerization technology such as docker and LXD, and the orchestration system for them like Kubernetes and Swarm. With the growing popularity of Cloud Native, the following problems have been raised: (i) most Cloud Native applications were designed for making full use of the cloud platform, but their file storage has not been completely optimized for adapting it. (ii) the traditional file system is designed as a utility for storing and retrieving files, usually built into the kernel of the operating systems. But when placing it to a large-scale condition, like a network storage server shared by thousands of computing instances, and stores millions of files, it will be slow and even unstable. (iii) most storage solutions use metadata for faster tracking of files, but the metadata itself will take up a lot of space, and the capacity of it is usually limited. If the file system store metadata directly into hard disk without caching, the tracking of massive small files will be a lot slower. (iv) The traditional object storage solution can't provide enough features to make itself more practical on the cloud such as caching and auto replication. This paper proposes a new storage engine based on the well-known Haystack storage engine, optimized in terms of service discovery and Automated fault tolerance, make it more suitable for Cloud Native infrastructure, deployment and applications. We use the object storage model to solve the large and high-frequency file storage needs, offering a simple and unified set of APIs for application to access. We also take advantage of Kubernetes' sophisticated and automated toolchains to make cloud storage easier to deploy, more flexible to scale, and more stable to run.

In order to solve the problems of the existing speech content authentication algorithm, such as single format, ununiversal algorithm, low security, low accuracy of tamper detection and location in small-scale, a multi-format speech perception hashing based on time-frequency parameter fusion of energy zero ratio and frequency band bariance is proposed. Firstly, the algorithm preprocesses the processed speech signal and calculates the short-time logarithmic energy, zero-crossing rate and frequency band variance of each speech fragment. Then calculate the energy to zero ratio of each frame, perform time- frequency parameter fusion on time-frequency features by mean filtering, and the time-frequency parameters are constructed by difference hashing method. Finally, the hash sequence is scrambled with equal length by logistic chaotic map, so as to improve the security of the hash sequence in the transmission process. Experiments show that the proposed algorithm is robustness, discrimination and key dependent.

In this letter, ferroelectric memory performance of TiN/Y-doped-HfO2 (HYO)/TiN capacitors is investigated under proton radiation with 3-MeV energy and different fluence (5e13, 1e14, 5e14, and 1e15 ions/cm2). X-ray diffraction patterns confirm that the orthorhombic phase Pbc21 of HYOfilm has no obvious change after proton radiation. Electrical characterization results demonstrate slight variations of the permittivity and ferroelectric hysteresis loop after proton radiation. The remanent polarization (2Pr) of the capacitor decreases with increasing proton fluence. But the decreasing trend of 2Pr is suppressed under high electric fields. Furthermore, the 2Pr degradation with cycling is abated by proton radiation. These results show that the HYO-based ferroelectric memory is highly resistive to proton radiation, which is potentially useful for space applications.

The tremendous growth of cloud computing and large-scale data analytics highlight the importance of reducing datacenter power consumption and environmental impact of brown energy. While many Internet service operators have at least partially powered their datacenters by green energy, it is challenging to effectively utilize green energy due to the intermittency of renewable sources, such as solar or wind. We find that the geographical diversity of internet-scale services can be carefully scheduled to improve the efficiency of applying green energy in datacenters. In this paper, we propose a holistic heterogeneity-aware cloud workload management approach, sCloud, that aims to maximize the system goodput in distributed self-sustainable datacenters. sCloud adaptively places the transactional workload to distributed datacenters, allocates the available resource to heterogeneous workloads in each datacenter, and migrates batch jobs across datacenters, while taking into account the green power availability and QoS requirements. We formulate the transactional workload placement as a constrained optimization problem that can be solved by nonlinear programming. Then, we propose a batch job migration algorithm to further improve the system goodput when the green power supply varies widely at different locations. Finally, we extend sCloud by integrating a flexible batch job manager to dynamically control the job execution progress without violating the deadlines. We have implemented sCloud in a university cloud testbed with real-world weather conditions and workload traces. Experimental results demonstrate sCloud can achieve near-to-optimal system performance while being resilient to dynamic power availability. sCloud with the flexible batch job management approach outperforms a heterogeneity-oblivious approach by 37 percent in improving system goodput and 33 percent in reducing QoS violations.

In view of the demand for the continuous guarantee capability of the information system in the diversified task and the complex cyber threat environment, a dual loop architecture of the resilient cloud environment for mission assurance is proposed. Firstly, general technical architecture of cloud environment is briefly introduced. Drawing on the idea of software definition, a resilient dual loop architecture based on "perception analysis planning adjustment" is constructed. Then, the core mission assurance system deployment mechanism is designed using the idea of distributed control. Finally, the core mission assurance system is designed in detail, which is consisted of six functional modules, including mission and environment awareness network, intelligent anomaly analysis and prediction, mission and resource situation generation, mission and resource planning, adaptive optimization and adjustment. The design of the dual loop architecture of the resilient cloud environment for mission assurance will further enhance the fast adaptability of the information system in the complex cyber physical environment.

Predicting software faults before software testing activities can help rational distribution of time and resources. Software metrics are used for software fault prediction due to their close relationship with software faults. Thanks to the non-linear fitting ability, Neural networks are increasingly used in the prediction model. We first filter metric set of the embedded software by statistical methods to reduce the dimensions of model input. Then we build a back propagation neural network with simple structure but good performance and apply it to two practical embedded software projects. The verification results show that the model has good ability to predict software faults.

With the implementation of W ⊕ X security model on computer system, Return-Oriented Programming(ROP) has become the primary exploitation technique for adversaries. Although many solutions that defend against ROP exploits have been proposed, they still suffer from various shortcomings. In this paper, we propose a new way to mitigate ROP attacks that are based on return instructions. We clean the scratch registers which are also the parameter registers based on the features of ROP malicious code and calling convention. A prototype is implemented on x64-based Linux platform based on Pin. Preliminary experimental results show that our method can efficiently mitigate conventional ROP attacks.

The barcode is an important link between real life and the virtual world nowadays. One of the most common barcodes is QR code, which its appearance, black and white modules, is not visually pleasing. The QR code is applied to product packaging and campaign promotion in the market. There are more and more stores using QR code for transaction payment. If the QR code is altered or illegally duplicated, it will endanger the information security of users. Therefore, the study uses infrared watermarking to embed the infrared QR code information into the explicit QR code to strengthen the anti-counterfeiting features. The explicit graphic QR code is produced by data hiding with error diffusion in this study. With the optical characteristics of K, one of the four printed ink colors CMYK (Cyan, Magenta, Yellow, Black), only K can be rendered in infrared. Hence, we use the infrared watermarking to embed the implicit QR code information into the explicit graphic QR code. General QR code reader may be used to interpret explicit graphic QR code information. As for implicit QR code, it needs the infrared detector to extract its implicit QR code information. If the QR code is illegally copied, it will not show the hidden second QR code under infrared detection. In this study, infrared watermark hidden in the graphic QR code can enhance not only the aesthetics of QR code, but also the anti-counterfeiting feature. It can also be applied to printing related fields, such as security documents, banknotes, etc. in the future.

Moving Target Defense (MTD) is a research hotspot in the field of network security. Moving Target Network Defense (MTND) is the implementation of MTD at network level. Numerous related works have been proposed in the field of MTND. In this paper, we focus on the scope and area of MTND, systematically present the recent representative progress from four aspects, including IP address and port mutation, route mutation, fingerprint mutation and multiple mutation, and put forward the future development directions. Several new perspectives and elucidations on MTND are rendered.

In this paper, we propose a deep learning framework for malware classification. There has been a huge increase in the volume of malware in recent years which poses a serious security threat to financial institutions, businesses and individuals. In order to combat the proliferation of malware, new strategies are essential to quickly identify and classify malware samples so that their behavior can be analyzed. Machine learning approaches are becoming popular for classifying malware, however, most of the existing machine learning methods for malware classification use shallow learning algorithms (e.g. SVM). Recently, Convolutional Neural Networks (CNN), a deep learning approach, have shown superior performance compared to traditional learning algorithms, especially in tasks such as image classification. Motivated by this success, we propose a CNN-based architecture to classify malware samples. We convert malware binaries to grayscale images and subsequently train a CNN for classification. Experiments on two challenging malware classification datasets, Malimg and Microsoft malware, demonstrate that our method achieves better than the state-of-the-art performance. The proposed method achieves 98.52% and 99.97% accuracy on the Malimg and Microsoft datasets respectively.

Industrial control systems are the fundamental infrastructures of a country. Since the intrusion attack methods for industrial control systems have become complex and concealed, the traditional protection methods, such as vulnerability database, virus database and rule matching cannot cope with the attacks hidden inside the terminals of industrial control systems. In this work, we propose a control flow anomaly detection algorithm based on the control flow of the business programs. First, a basic group partition method based on key paths is proposed to reduce the performance burden caused by tabbed-assert control flow analysis method through expanding basic research units. Second, the algorithm phases of standard path set acquisition and path matching are introduced. By judging whether the current control flow path is deviating from the standard set or not, the abnormal operating conditions of industrial control can be detected. Finally, the effectiveness of a control flow anomaly detection (checking) algorithm based on Path Matching (CFCPM) is demonstrated by anomaly detection ability analysis and experiments.