Biblio

With the proliferation of cloud services, cloud-based image retrieval services enable large-scale image outsourcing and ubiquitous image searching. While enjoying the benefits of the cloud-based image retrieval services, critical privacy concerns may arise in such services since they may contain sensitive personal information. In this paper, we propose an efficient and Privacy-Preserving Image Retrieval scheme with Key Switching Technique (PPIRS). PPIRS utilizes the inner product encryption for measuring Euclidean distances between image feature vectors and query vectors in a privacy-preserving manner. Due to the high dimension of the image feature vectors and the large scale of the image databases, traditional secure Euclidean distance comparison methods provide insufficient search efficiency. To prune the search space of image retrieval, PPIRS tailors key switching technique (KST) for reducing the dimension of the encrypted image feature vectors and further achieves low communication overhead. Meanwhile, by introducing locality sensitive hashing (LSH), PPIRS builds efficient searchable indexes for image retrieval by organizing similar images into a bucket. Security analysis shows that the privacy of both outsourced images and queries are guaranteed. Extensive experiments on a real-world dataset demonstrate that PPIRS achieves efficient image retrieval in terms of computational cost.

Information-Centric Networking (ICN) has attracted much attention as a promising future network design, which presents a paradigm shift from host-centric to content-centric. However, in edge computing scenarios, there is still no specific ICN forwarding mechanism to improve transmission performance. In this paper, we propose an edge-oriented forwarding mechanism (EFM) for edge computing scenarios. The rationale is to enable edge nodes smarter, such as acting as agents for both consumers and providers to improve content retrieval and distribution. On the one hand, EFM can assist consumers: the edge router can be used either as a fast content repository to satisfy consumers’ requests or as a smart delegate of consumers to request content from upstream nodes. On the other hand, EFM can assist providers: EFM leverages the optimized in-network recovery/retransmission to detect packet loss or even accelerate the content distribution. The goal of our research is to improve the performance of edge networks. Simulation results based on ndnSIM indicate that EFM can enable efficient content retrieval and distribution, friendly to both consumers and providers.

Ahstract-Vulnerability detection is an important topic of software engineering. To improve the effectiveness and efficiency of vulnerability detection, many traditional machine learning-based and deep learning-based vulnerability detection methods have been proposed. However, the impact of different factors on vulnerability detection is unknown. For example, classification models and vectorization methods can directly affect the detection results and code replacement can affect the features of vulnerability detection. We conduct a comparative study to evaluate the impact of different classification algorithms, vectorization methods and user-defined variables and functions name replacement. In this paper, we collected three different vulnerability code datasets. These datasets correspond to different types of vulnerabilities and have different proportions of source code. Besides, we extract and analyze the features of vulnerability code datasets to explain some experimental results. Our findings from the experimental results can be summarized as follows: (i) the performance of using deep learning is better than using traditional machine learning and BLSTM can achieve the best performance. (ii) CountVectorizer can improve the performance of traditional machine learning. (iii) Different vulnerability types and different code sources will generate different features. We use the Random Forest algorithm to generate the features of vulnerability code datasets. These generated features include system-related functions, syntax keywords, and user-defined names. (iv) Datasets without user-defined variables and functions name replacement will achieve better vulnerability detection results.

This paper proposes a stream cipher algorithm. Its main principle is conducting the binary random dynamic hash with the help of key. At the same time of calculating the hash mapping address of plaintext, change the value of plaintext through bits scrambling, and then map it to the ciphertext space. This encryption method has strong randomness, and the design of hash functions and bits scrambling is flexible and diverse, which can constitute a set of encryption and decryption methods. After testing, the code evenness of the ciphertext obtained using this method is higher than that of the traditional method under some extreme conditions..

In the existing scheduling algorithms of mimicry structure, the random algorithm cannot solve the problem of large vulnerability window in the process of random scheduling. Based on known vulnerabilities, the algorithm with diversity and complexity as scheduling indicators can not only fail to meet the characteristic requirements of mimic's endogenous security for defense, but also cannot analyze the unknown vulnerabilities and measure the continuous differences in time of mimic Executive Entity. In this paper, from the Angle of attack surface is put forward based on mimicry attack the mimic Executive Entity scheduling algorithm, its resources to measure analysis method and mimic security has intrinsic consistency, avoids the random algorithm to vulnerability and modeling using known vulnerabilities targeted, on time at the same time can ensure the diversity of the Executive body, to mimic the attack surface web server scheduling system in continuous time is less, and able to form a continuous differences. Experiments show that the minimum symbiotic resource scheduling algorithm based on time continuity is more secure than the random scheduling algorithm.

In this paper, we present a flexible Variable Precision Computation Array (VPCA) component for different accelerators, which leverages a sparsification scheme for activations and a low bits serial-parallel combination computation unit for improving the efficiency and resiliency of accelerators. The VPCA can dynamically decompose the width of activation/weights (from 32bit to 3bit in different accelerators) into 2-bits serial computation units while the 2bits computing units can be combined in parallel computing for high throughput. We propose an on-the-fly compressing and calculating strategy SLE-CLC (single lane encoding, cross lane calculation), which could further improve performance of 2-bit parallel computing. The experiments results on image classification datasets show VPCA can outperforms DaDianNao, Stripes, Loom-2bit by 4.67×, 2.42×, 1.52× without other overhead on convolution layers.

Clustering is a concept in data mining, which divides a data set into different classes or clusters according to a specific standard, making the similarity of data objects in the same cluster as large as possible. Clustering by fast search and find of density peaks (DPC) is a novel clustering algorithm based on density. It is simple and novel, only requiring fewer parameters to achieve better clustering effect, without the requirement for iterative solution. And it has expandability and can detect the clustering of any shape. However, DPC algorithm still has some defects, such as it employs the clear neighborhood relations to calculate local density, so it cannot identify the neighborhood membership of different values of points from the distance of points and It is impossible to accurately cluster the data of the multi-density peak. The fuzzy neighborhood density peak clustering algorithm is proposed for this shortcoming (F-DPC): novel local density is defined by the fuzzy neighborhood relationship. The fuzzy set theory can be used to make the fuzzy neighborhood function of local density more sensitive, so that the clustering for data set of various shapes and densities is more robust. Experiments show that the algorithm has high accuracy and robustness.

Cyber-Physical Systems (CPS) such as intelligent connected vehicles, smart farming and smart logistics are constantly generating tons of data and requiring real-time data processing capabilities. Therefore, Edge Computing which provisions computing resources close to the End Devices from the network edge is becoming the ideal platform for CPS. However, it also brings many issues and one of the most prominent challenges is how to ensure the development of trustworthy smart services given the dynamic and distributed nature of Edge Computing. To tackle this challenge, this paper proposes a novel Federated Learning based Edge Computing platform for CPS, named “FengHuoLun”. Specifically, based on FengHuoLun, we can: 1) implement smart services where machine learning models are trained in a trusted Federated Learning framework; 2) assure the trustworthiness of smart services where CPS behaviours are tested and monitored using the Federated Learning framework. As a work in progress, we have presented an overview of the FengHuoLun platform and also some preliminary studies on its key components, and finally discussed some important future research directions.

In more electrical aircraft, the embedded electrical network is handling more and more vital functions, being more and more strained as well. Attenuation of switching harmonics is a key step in the network reliability, thus filtering elements play a central role. To keep the weight of the embedded network reasonable, weakly damped high-order filters shall be preferred. Flatness-based control (FBC) can offer both high bandwidth regulation and large signal stability proof. This make FBC a good candidate to handle the inherent oscillating behavior of aforementioned filters. However, this control strategy can be tricky to implement, especially with high order systems. Moreover, FBC is more sensor demanding than classic PI-based control. This paper address these two drawbacks. First, a novel trajectory planning for high order systems is proposed. This method does not require multiple derivations. Then the input sensors are removed thanks to a parameters estimator. Feasibility and performances are verified with experimental results. Performances comparison with cascaded-loop topologies are given in final section to prove the relevance of the proposed control strategy.

The industrial Internet of Things (IIoT) can facilitate industrial upgrading, intelligent manufacturing, and lean production. Industrial control system (ICS) is a vital support mechanism for many key infrastructures in the IIoT. However, natural defects in the ICS network security mechanism and the susceptibility of the programmable logic controller (PLC) program to malicious attack pose a threat to the safety of national infrastructure equipment. To improve the security of the underlying equipment in ICS, a model checking method based on timed automata is proposed in this work, which can effectively model the control process and accurately simulate the system state when incorporating time factors. Formal analysis of the ICS and PLC is then conducted to formulate malware detection rules which can constrain the normal behavior of the system. The model checking tool UPPAAL is then used to verify the properties by detecting whether there is an exception in the system and determine the behavior of malware through counter-examples. The chemical reaction control system in Tennessee-Eastman process is taken as an example to carry out modeling, characterization, and verification, and can effectively detect multiple patterns of malware and propose relevant security policy recommendations.

Recently, several practical attacks raised serious concerns over the security of searchable encryption. The attacks have brought emphasis on forward privacy, which is the key concept behind solutions to the adaptive leakage-exploiting attacks, and will very likely to become a must-have property of all new searchable encryption schemes. For a long time, forward privacy implies inefficiency and thus most existing searchable encryption schemes do not support it. Very recently, Bost (CCS 2016) showed that forward privacy can be obtained without inducing a large communication overhead. However, Bost's scheme is constructed with a relatively inefficient public key cryptographic primitive, and has poor I/O performance. Both of the deficiencies significantly hinder the practical efficiency of the scheme, and prevent it from scaling to large data settings. To address the problems, we first present FAST, which achieves forward privacy and the same communication efficiency as Bost's scheme, but uses only symmetric cryptographic primitives. We then present FASTIO, which retains all good properties of FAST, and further improves I/O efficiency. We implemented the two schemes and compared their performance with Bost's scheme. The experiment results show that both our schemes are highly efficient.

The emergence of the Internet of Things with its constraints obliges researchers in this field to find light and accurate solutions to secure the data exchange. This document presents secure authentication using biometrics coupled with an effective key agreement scheme to save time and energy. In our scheme, the agreed key is used to encrypt transmission data between different IoT actors. While the fuzzy extractor based on the fuzzy vault principle, is used as authentication and as key agreement scheme. Besides, our system incorporates the Reed Solomon and Hamming codes to give some tolerance to errors. The experimental results have been discussed according to several recognition rates and computation times. Indeed, the recognition rate results have been compared to other works to validate our system. Also, we clarify how our system resists to specific transmission attacks without affecting lightness and accuracy.

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.

Designing an efficient difficulty control algorithm is an essential problem in Proof-of-Work (PoW) based blockchains because the network hash rate is randomly changing. This paper proposes a general difficulty control algorithm and provides insights for difficulty adjustment rules for PoW based blockchains. The proposed algorithm consists a two-layer neural network. It has low memory cost, meanwhile satisfying the fast-updating and low volatility requirements for difficulty adjustment. Real data from Ethereum are used in the simulations to prove that the proposed algorithm has better performance for the control of the block difficulty.

Big data analytics, in essence, is becoming the revolution of business intelligence around the world. This momentum has given rise to the hype around analytic technologies, including Apache Hadoop. Hadoop was not originally developed with security in mind. Despite the evolving efforts to integrate security in Hadoop through developing new tools (e.g., Apache Sentry and Ranger) and employing traditional mechanisms (e.g., Kerberos and LDAP), they mainly focus on providing encryption and authentication features, albeit with limited authorization support. Existing solutions in the literature extended these evolving efforts. However, they suffer from limitations, hindering them from providing robust authorization that effectively meets the unique requirements of big data environments. Towards covering this gap, this paper proposes a hybrid authority (HBD-Authority) as a formal attribute-based access control model with context support. This model is established on a novel hybrid approach of authorization transparency that pertains to three fundamental properties of accuracy: correctness, security, and completeness. The model leverages streaming data analytics to foster distributed parallel processing capabilities that achieve multifold benefits: a) efficiently managing the security policies and promptly updating the privileges assigned to a high number of users interacting with the analytic services; b) swiftly deciding and enforcing authorization of requests over data characterized by the 5Vs; and c) providing dynamic protection for data which is frequently updated. The implementation details and experimental evaluation of the proposed model are presented, demonstrating its performance efficiency.

Hierarchical Text classification has recently become increasingly challenging with the growing number of classification labels. In this paper, we propose a hierarchical fine-tuning based approach for hierarchical text classification. We use the ordered neurons LSTM (ONLSTM) model by combining the embedding of text and parent category for hierarchical text classification with a large number of categories, which makes full use of the connection between the upper-level and lower-level labels. Extensive experiments show that our model outperforms the state-of-the-art hierarchical model at a lower computation cost.

Information-centric networking (ICN) has played an increasingly important role in the next generation network design. However, to make better use of request-response communication mode in the ICN network, revoke user privileges more efficiently and protect user privacy more safely, an effective access control mechanism is needed. In this paper, we propose IBSS (identity-based secret sharing), which achieves efficient content distribution by using improved Shamir's secret sharing method. At the same time, collusion attacks are avoided by associating polynomials' degree with the number of users. When authenticating user identity and transmitting content, IBE and IBS are introduced to achieve more efficient and secure identity encryption. From the experimental results, the scheme only introduces an acceptable delay in file retrieval, and it can request follow-up content very efficiently.

Dynamic security assessment (DSA) is to ensure the power system being operated under a secure condition that can withstand potential contingencies. DSA normally proceeds periodically on a 5 to 15 minutes basis, where the system security condition over a complete time interval is merely determined upon the system snapshot captured at the beginning of the interval. With high wind power penetration, the minute-to-minute variations of wind power can lead to more volatile power system states within a single DSA time interval. This paper investigates the intra-interval variation (IIV) phenomenon in power system online DSA and analyze whether the IIV problem is deserved attention in future DSA research and applications. An IIV-contaminated testing environment based on hierarchical Monte-Carlo simulation is developed to evaluate the practical IIV impacts on power system security and DSA performance. The testing results show increase in system insecurity risk and significant degradation in DSA accuracy in presence of IIV. This result draws attention to the IIV phenomenon in DSA of wind-energy power systems and calls for more robust DSA approach to mitigate the IIV impacts.

Style transfer produces a transferred image which is a rendering of a content image in the manner of a style image. We seek to understand how to improve style transfer.To do so requires quantitative evaluation procedures, but current evaluation is qualitative, mostly involving user studies. We describe a novel quantitative evaluation procedure. Our procedure relies on two statistics: the Effectiveness (E) statistic measures the extent that a given style has been transferred to the target, and the Coherence (C) statistic measures the extent to which the original image's content is preserved. Our statistics are calibrated to human preference: targets with larger values of E and C will reliably be preferred by human subjects in comparisons of style and content, respectively.We use these statistics to investigate relative performance of a number of Neural Style Transfer (NST) methods, revealing a number of intriguing properties. Admissible methods lie on a Pareto frontier (i.e. improving E reduces C, or vice versa). Three methods are admissible: Universal style transfer produces very good C but weak E; modifying the optimization used for Gatys' loss produces a method with strong E and strong C; and a modified cross-layer method has slightly better E at strong cost in C. While the histogram loss improves the E statistics of Gatys' method, it does not make the method admissible. Surprisingly, style weights have relatively little effect in improving EC scores, and most variability in transfer is explained by the style itself (meaning experimenters can be misguided by selecting styles). Our GitHub Link is available1.

Object identification in the room environment is a key technique in many advanced engineering applications such as the unidentified object recognition in security surveillance, human identification and barrier recognition for AI robots. The identification technique based on the sound field perturbation analysis is capable of giving immersive identification which avoids the occlusion problem in the traditional vision-based method. In this paper, a new insight into the relation between the object and the variation of the sound field is presented. The sound field difference before and after the object locates in the environment is analyzed using the spectral subtraction based on the room impulse response. The spectral subtraction shows that the energy loss caused by the sound absorption is the essential factor which perturbs the sound field. By using the energy loss with high uniqueness as the extracted feature, an object identification technique is constructed under the classical supervised pattern recognition framework. The experiment in a real room validates that the system has high identification accuracy. In addition, based on the feature property of position insensitivity, this technique can achieve high identifying accuracy with a quite small training data set, which demonstrates that the technique has potential to be used in real engineering applications.

We consider information leakage to the user in private information retrieval (PIR) systems. Information leakage can be measured in terms of individual message leakage or total leakage. Individual message leakage, or simply individual leakage, is defined as the amount of information that the user can obtain on any individual message that is not being requested, and the total leakage is defined as the amount of information that the user can obtain about all the other messages except the one being requested. In this work, we characterize the tradeoff between the minimum download cost and the individual leakage, and that for the total leakage, respectively. Coding schemes are proposed to achieve these optimal tradeoffs, which are also shown to be optimal in terms of the message size. We further characterize the optimal tradeoff between the minimum amount of common randomness and the total leakage. Moreover, we show that under individual leakage, common randomness is in fact unnecessary when there are more than two messages.

Approximate nearest neighbour search (ANNS) in high dimensional space is a fundamental problem in many applications, such as multimedia database, computer vision and information retrieval. Among many solutions, data-sensitive hashing-based methods are effective to this problem, yet few of them are designed for external storage scenarios and hence do not optimized for I/O efficiency during the query processing. In this paper, we introduce a novel data-sensitive indexing and query processing framework for ANNS with an emphasis on optimizing the I/O efficiency, especially, the sequential I/Os. The proposed index consists of several lists of point IDs, ordered by values that are obtained by learned hashing (i.e., mapping) functions on each corresponding data point. The functions are learned from the data and approximately preserve the order in the high-dimensional space. We consider two instantiations of the functions (linear and non-linear), both learned from the data with novel objective functions. We also develop an I/O efficient ANNS framework based on the index. Comprehensive experiments on six benchmark datasets show that our proposed methods with learned index structure perform much better than the state-of-the-art external memory-based ANNS methods in terms of I/O efficiency and accuracy.

As a typical representative of a new generation military information technology, the value and significance of Internet of Battlefield Things (IoBT) has been widely recognized by the world's military forces. At the same time, Internet of Battlefield Things (IoBT) is facing serious scalability and security challenges. This paper presents the basic concept and six-domain model of IoBT, explains the integration security framework of IoBT and blockchain. Furthermore, we design and build a novel IoT framework called IoBTChain based on blockchain and smart contracts, which adopts a credit-based resource management system to control the amount of resources that an IoBT device can obtain from a cloud server based on pre-defined priority rules, application types, and behavior history. We illustrate the deployment procedure of blockchain and smart contracts, the device registration procedure on blockchain, the IoBT behavior regulation workflow and the pricing-based resource allocation algorithm.

To find software vulnerabilities using software vulnerability detection technology is an important way to ensure the system security. Existing software vulnerability detection methods have some limitations as they can only play a certain role in some specific situations. To accurately analyze and evaluate the existing vulnerability detection methods, an integrated testing and evaluation system (iTES) is designed and implemented in this paper. The main functions of the iTES are:(1) Vulnerability cases with source codes covering common vulnerability types are collected automatically to form a vulnerability cases library; (2) Fourteen methods including static and dynamic vulnerability detection are evaluated in iTES, involving the Windows and Linux platforms; (3) Furthermore, a set of evaluation metrics is designed, including accuracy, false positive rate, utilization efficiency, time cost and resource cost. The final evaluation and test results of iTES have a good guiding significance for the selection of appropriate software vulnerability detection methods or tools according to the actual situation in practice.

With the gradual advancement of smart city construction, various information systems have been widely used in smart cities. In order to obtain huge economic benefits, criminals frequently invade the information system, which leads to the increase of malware. Malware attacks not only seriously infringe on the legitimate rights and interests of users, but also cause huge economic losses. Signature-based malware detection algorithms can only detect known malware, and are susceptible to evasion techniques such as binary obfuscation. Behavior-based malware detection methods can solve this problem well. Although there are some malware behavior analysis works, they may ignore semantic information in the malware API call sequence. In this paper, we design a joint framework based on local and global features for malware detection to solve the problem of network security of smart cities, called LGMal, which combines the stacked convolutional neural network and graph convolutional networks. Specially, the stacked convolutional neural network is used to learn API call sequence information to capture local semantic features and the graph convolutional networks is used to learn API call semantic graph structure information to capture global semantic features. Experiments on Alibaba Cloud Security Malware Detection datasets show that the joint framework gets better results. The experimental results show that the precision is 87.76%, the recall is 88.08%, and the F1-measure is 87.79%. We hope this paper can provide a useful way for malware detection and protect the network security of smart city.