Biblio

Existing cyber security solutions have been basically developed using knowledge-based models that often cannot trigger new cyber-attack families. With the boom of Artificial Intelligence (AI), especially Deep Learning (DL) algorithms, those security solutions have been plugged-in with AI models to discover, trace, mitigate or respond to incidents of new security events. The algorithms demand a large number of heterogeneous data sources to train and validate new security systems. This paper presents the description of new datasets, the so-called ToNİoT, which involve federated data sources collected from Telemetry datasets of IoT services, Operating system datasets of Windows and Linux, and datasets of Network traffic. The paper introduces the testbed and description of TONİoT datasets for Windows operating systems. The testbed was implemented in three layers: edge, fog and cloud. The edge layer involves IoT and network devices, the fog layer contains virtual machines and gateways, and the cloud layer involves cloud services, such as data analytics, linked to the other two layers. These layers were dynamically managed using the platforms of software-Defined Network (SDN) and Network-Function Virtualization (NFV) using the VMware NSX and vCloud NFV platform. The Windows datasets were collected from audit traces of memories, processors, networks, processes and hard disks. The datasets would be used to evaluate various AI-based cyber security solutions, including intrusion detection, threat intelligence and hunting, privacy preservation and digital forensics. This is because the datasets have a wide range of recent normal and attack features and observations, as well as authentic ground truth events. The datasets can be publicly accessed from this link [1].

We leverage deep learning algorithms on various user behavioral information gathered from end-user devices to classify a subject of interest. In spite of the ability of these techniques to counter spoofing threats, they are vulnerable to adversarial learning attacks, where an attacker adds adversarial noise to the input samples to fool the classifier into false acceptance. Recently, a handful of mature techniques like Fast Gradient Sign Method (FGSM) have been proposed to aid white-box attacks, where an attacker has a complete knowledge of the machine learning model. On the contrary, we exploit a black-box attack to a behavioral biometric system based on gait patterns, by using FGSM and training a shadow model that mimics the target system. The attacker has limited knowledge on the target model and no knowledge of the real user being authenticated, but induces a false acceptance in authentication. Our goal is to understand the feasibility of a black-box attack and to what extent FGSM on shadow models would contribute to its success. Our results manifest that the performance of FGSM highly depends on the quality of the shadow model, which is in turn impacted by key factors including the number of queries allowed by the target system in order to train the shadow model. Our experimentation results have revealed strong relationships between the shadow model and FGSM performance, as well as the effect of the number of FGSM iterations used to create an attack instance. These insights also shed light on deep-learning algorithms' model shareability that can be exploited to launch a successful attack.

The performance-driven design of SDN architectures leaves many security vulnerabilities, a notable one being the communication bottleneck between the controller and the switches. Functioning as a cache between the controller and the switches, the flow table mitigates this bottleneck by caching flow rules received from the controller at each switch, but is very limited in size due to the high cost and power consumption of the underlying storage medium. It thus presents an easy target for attacks. Observing that many existing defenses are based on simplistic attack models, we develop a model of intelligent attacks that exploit specific cache-like behaviors of the flow table to infer its internal configuration and state, and then design attack parameters accordingly. Our evaluations show that such attacks can accurately expose the internal parameters of the target flow table and cause measurable damage with the minimum effort.

K-Nearest Neighbor (k-NN) search is one of the most commonly used approaches for similarity search. It finds extensive applications in machine learning and data mining. This era of big data warrants efficiently scaling k-NN search algorithms for billion-scale datasets with high dimensionality. In this paper, we propose a solution towards this end where we use vantage point trees for partitioning the dataset across multiple processes and exploit an existing graph-based sequential approximate k-NN search algorithm called HNSW (Hierarchical Navigable Small World) for searching locally within a process. Our hybrid MPI-OpenMP solution employs techniques including exploiting MPI one-sided communication for reducing communication times and partition replication for better load balancing across processes. We demonstrate computation of k-NN for 10,000 queries in the order of seconds using our approach on 8000 cores on a dataset with billion points in an 128-dimensional space. We also show 10X speedup over a completely k-d tree-based solution for the same dataset, thus demonstrating better suitability of our solution for high dimensional datasets. Our solution shows almost linear strong scaling.

Advances in sensing and tracking technology lead to the proliferation of location-based services. Location service providers (LSPs) often resort to commercial public clouds to store the tremendous geospatial data and process location-based queries from data users. To protect the privacy of LSP's geospatial data and data user's query location against the untrusted cloud, they are required to be encrypted before sending to the cloud. Nevertheless, it is not easy to design a fast and secure location-based query processing scheme over the encrypted data. In this paper, we propose a Fast and Secure kNN (FSkNN) scheme to support secure k nearest neighbor (k NN) search in cloud computing. We reveal the inherent connection between an Sk NN protocol and a secure range query protocol and further describe how to construct FSkNN based on a secure range query protocol. FSkNN leverages a customized accuracy-assured strategy to ensure the result accuracy and adopts a data structure named random Bloom filter (RBF) to build a secure index for efficiently searching. We formally prove the security of FSkNN under the random oracle model. Our evaluation results show that FSkNN is highly practical.

Named Data Network's (NDN) data-centric approach makes it a suitable solution in a networking scenario where there are connectivity issues as a result of the dynamism of the network. Coupling of this ability with the blockchain's well-documented immutable trustworthy-distributed ledger feature, the union of blockchain and NDN in an Internet-of-Battlefield-Things (IoBT) setting could prove to be the ideal alliance that would guarantee data exchanged in an IoBT environment is trusted and less susceptible to cyber-attacks and packet losses. Various blockchain technologies, however, require that each node has a ledger that stores information or transactions in a chain of blocks. This poses an issue as nodes in an IoBT setting have varying computing and storage resources. Moreover, most of the nodes in the IoT/IoBT network are plagued with limited resources. As such, there needs to be an approach that ensures that the limited resources of these nodes are efficiently utilized. In this paper, we investigate an approach that merges blockchain and NDN to efficiently utilize the resources of these resource-constrained nodes by only storing relevant information on each node's ledger. Furthermore, we propose a sharding technique called an Interest Group and introduce a novel consensus mechanism called Proof of Common Interest. Performance of the proposed approach is evaluated using numerical results.

Current physical layer authentication (PLA) mechanisms are mostly designed for static communications, and the accuracy degrades significantly when used in dynamic scenarios, where the network environments and wireless channels change frequently. To improve the authentication performance, it is necessary to update the hypothesis test models and parameters in time, which however brings high computational complexity and authentication delay. In this paper, we propose a lightweight cross-layer authentication scheme for dynamic communication scenarios. We use multiple characteristics based PLA to guarantee the reliability and accuracy of authentication, and propose an upper layer assisted method to ensure the performance stability. Specifically, upper layer authentication (ULA) helps to update the PLA models and parameters. By properly choosing the period of triggering ULA, a balance between complexity and performance can be easily obtained. Simulation results show that our scheme can achieve pretty good authentication performance with reduced complexity.

Cryptography is the method of transforming the original texted message into an unknown form and in reverse also. It is the process of hiding and forwarding the data in an appropriate form so that only authorized persons can know and can process it. Cryptographic process secures the data from hijacking or transmutation, it is mainly used for users data security. This paper justifies the encryption and decryption using DNA(Deoxyribo Nucleic Acid) sequence. This process includes several intermediate steps, the perception of binary-coded form and generating of arbitrary keys is used to encrypt the message. A common key should be established between the sender and receiver for encryption and decryption process. The common key provides more security to the sequence. In this paper, both the process of binary-coded form and generating of arbitrary keys are used to encrypt the message. It is widely used in an institution and by every individual to hide their data from the muggers and hijackers and provides the data securely, and confidentially over the transmission of information.

New technologies, such as augmented reality (AR) are used to enhance human capabilities and extend human functioning; nevertheless they may cause distraction and incorrect human functioning. Systems including socio entities (such as human) and technical entities (such as augmented reality) are called socio-technical systems. In order to do risk assessment in such systems, considering new dependability threats caused by augmented reality is essential, for example failure of an extended human function is a new type of dependability threat introduced to the system because of new technologies. In particular, it is required to identify these new dependability threats and extend modeling and analyzing techniques to be able to uncover their potential impacts. This research aims at providing a framework for risk assessment in AR-equipped socio-technical systems by identifying AR-extended human failures and AR-caused faults leading to human failures. Our work also extends modeling elements in an existing metamodel for modeling socio-technical systems, to enable AR-relevant dependability threats modeling. This extended metamodel is expected to be used for extending analysis techniques to analyze AR-equipped socio-technical systems.

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.

With the shift in storage paradigm, there is an increasing need for privacy of dataset and also for an encryption scheme that permits computation on encrypted data. Paillier cryptosystem is a good example of such a homomorphic encryption scheme. To improve the efficiency of the Paillier homomorphic encryption scheme in terms of its decryption speed and overall computational cost, we propose an improved decryption process. Specifically, the inclusion of a variable k to reduce the modular multiplicative arithmetic. The variable k is combined with the L function and CRT recombination method, to arrive at a fast and improved decryption process, showing the mathematical correctness of the decryption algorithm. Experimental results validate that our scheme is significantly efficient in its decryption speed.

In network communication domain, one of the most widely used protocol for encrypting data and securing communications is the IPSec protocol. The design of this protocol is based on two main phases which are: exchanging keys phase and transferring data phase. In this paper we focus on enhancing the exchanging keys phase which is included in the security association (SA), using a chaotic cryptosystem. Initially IPSec is based on the Internet Key Exchange (IKE) protocol for establishing the SA. Actually IKE protocol is in charge for negotiating the connection and for authenticating both nodes. However; using IKE gives rise to a major problem related to security attack such as the Man in the Middle Attack. In this paper, we propose a chaotic cryptosystem solution to generate SA file for the connected nodes of the network. By solving a 4-Dimension chaotic system, a SA file that includes 128-bit keys will be established. The proposed solution is implemented and tested using FPGA boards.

Context : Programmers frequently look for the code of previously solved problems that they can adapt for their own problem. Despite existing example code on the web, on sites like Stack Overflow, cryptographic Application Programming Interfaces (APIs) are commonly misused. There is little known about what makes examples helpful for developers in using crypto APIs. Analogical problem solving is a psychological theory that investigates how people use known solutions to solve new problems. There is evidence that the capacity to reason and solve novel problems a.k.a Fluid Intelligence (Gf) and structurally and procedurally similar solutions support problem solving. Aim: Our goal is to understand whether similarity and Gf also have an effect in the context of using cryptographic APIs with the help of code examples. Method : We conducted a controlled experiment with 76 student participants developing with or without procedurally similar examples, one of two Java crypto libraries and measured the Gf of the participants as well as the effect on usability (effectiveness, efficiency, satisfaction) and security bugs. Results: We observed a strong effect of code examples with a high procedural similarity on all dependent variables. Fluid intelligence Gf had no effect. It also made no difference which library the participants used. Conclusions: Example code must be more highly similar to a concrete solution, not very abstract and generic to have a positive effect in a development task.

Mechanical faults of Gas Insulated Switchgear (GIS) often occurred, which may cause serious losses. Detecting vibration signal was effective for condition monitoring and fault diagnosis of GIS. The vibration characteristic of GIS in service was detected and researched based on a developed testing system in this paper, and feature fingerprint extraction method was proposed to evaluate vibration characteristics and diagnose mechanical defects. Through analyzing the spectrum of the vibration signal, we could see that vibration frequency of operating GIS was about 100Hz under normal condition. By means of the wavelet transformation, the vibration fingerprint was extracted for the diagnosis of mechanical vibration. The mechanical vibration characteristic of GIS including circuit breaker and arrester in service was detected, we could see that the frequency distribution of abnormal vibration signal was wider, it contained a lot of high harmonic components besides the 100Hz component, and the vibration acoustic fingerprint was totally different from the normal ones, that is, by comparing the frequency spectra and vibration fingerprint, the mechanical faults of GIS could be found effectively.

The fuzzy query scheme based on vector index uses Bloom filter to construct vector index for key words. Then the statistical attack based on the deviation of frequency distribution of the vector index brings out the sensitive information disclosure. Using the noise vector, a fuzzy query scheme resistant to the statistical attack serving for encrypted database, i.e. S-BF, is introduced. With the noise vector to clear up the deviation of frequency distribution of vector index, the statistical attacks to the vector index are resolved. Demonstrated by lab experiment, S-BF scheme can achieve the secure fuzzy query with the powerful privation protection capability for encrypted cloud database without the loss of fuzzy query efficiency.

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.

Malware has remained a consistent threat since its emergence, growing into a plethora of types and in large numbers. In recent years, numerous new malware variants have enabled the identification of new attack surfaces and vectors, and have become a major challenge to security experts, driving the enhancement and development of new malware analysis techniques to contain the contagion. One of the preliminary steps of malware analysis is to remove the abundance of counterfeit malware samples from the large collection of suspicious samples. This process assists in the management of man and machine resources effectively in the analysis of both unknown and likely malware samples. Hashing techniques are one of the fastest and efficient techniques for performing this preliminary analysis such as fuzzy hashing and import hashing. However, both hashing methods have their limitations and they may not be effective on their own, instead the combination of two distinctive methods may assist in improving the detection accuracy and overall performance of the analysis. This paper proposes a Fuzzy-Import hashing technique which is the combination of fuzzy hashing and import hashing to improve the detection accuracy and overall performance of malware analysis. This proposed Fuzzy-Import hashing offers several benefits which are demonstrated through the experimentation performed on the collected malware samples and compared against stand-alone techniques of fuzzy hashing and import hashing.

Cipher Text Policy Attribute Based Encryption which is a form of Public Key Encryption has become a renowned approach as a Data access control scheme for data security and confidentiality. It not only provides the flexibility and scalability in the access control mechanisms but also enhances security by fuzzy fined-grained access control. However, schemes are there which for more security increases the key size which ultimately leads to high encryption and decryption time. Also, there is no provision for handling the middle man attacks during data transfer. In this paper, a light-weight and more scalable encryption mechanism is provided which not only uses fewer resources for encoding and decoding but also improves the security along with faster encryption and decryption time. Moreover, this scheme provides an efficient key sharing mechanism for providing secure transfer to avoid any man-in-the-middle attacks. Also, due to fuzzy policies inclusion, chances are there to get approximation of user attributes available which makes the process fast and reliable and improves the performance of legitimate users.

The purpose of this work is to analyze the security model of a robotized system, to analyze the approaches to assessing the security of this system, and to develop our own framework. The solution to this problem involves the use of developed frameworks. The analysis will be conducted on a robotic system of robots. The prefix structures assume that the robotic system is divided into levels, and after that it is necessary to directly protect each level. Each level has its own characteristics and drawbacks that must be considered when developing a security system for a robotic system.

Blockchains and distributed ledgers have brought renewed interest in Byzantine fault-tolerant protocols and decentralized systems, two domains studied for several decades. Recent promising works have in particular proposed to use epidemic protocols to overcome the limitations of popular Blockchain mechanisms, such as proof-of-stake or proof-of-work. These works unfortunately assume a perfect peer-sampling service, immune to malicious attacks, a property that is difficult and costly to achieve. We revisit this fundamental problem in this paper, and propose a novel Byzantine-tolerant peer-sampling service that is resilient to Sybil attacks in open systems by exploiting the underlying structure of wide-area networks.

To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic. Similarly, a chatbot may need to customize its communication style to improve engagement with its audience. This manner of changing the style of written text has gained significant attention in recent years. Yet these past research works largely cater to the transfer of single style attributes. The disadvantage of focusing on a single style alone is that this often results in target text where other existing style attributes behave unpredictably or are unfairly dominated by the new style. To counteract this behavior, it would be nice to have a style transfer mechanism that can transfer or control multiple styles simultaneously and fairly. Through such an approach, one could obtain obfuscated or written text incorporated with a desired degree of multiple soft styles such as female-quality, politeness, or formalness. To the best of our knowledge this work is the first that shows and attempt to solve the issues related to multiple style transfer. We also demonstrate that the transfer of multiple styles cannot be achieved by sequentially performing multiple single-style transfers. This is because each single style-transfer step often reverses or dominates over the style incorporated by a previous transfer step. We then propose a neural network architecture for fairly transferring multiple style attributes in a given text. We test our architecture on the Yelp dataset to demonstrate our superior performance as compared to existing one-style transfer steps performed in a sequence.

With the increasing performance of neural networks on many security-critical tasks, the security concerns of machine learning have become increasingly prominent. Recent studies have shown that neural networks are vulnerable to adversarial examples: carefully crafted inputs with negligible perturbations on legitimate samples could mislead a neural network to produce adversary-selected outputs while humans can still correctly classify them. Therefore, we need an additional measurement on the trustworthiness of the results of a machine learning model, especially in adversarial settings. In this paper, we analyse the root cause of adversarial examples, and propose a new property, namely fidelity, of machine learning models to describe the gap between what a model learns and the ground truth learned by humans. One of its benefits is detecting adversarial attacks. We formally define fidelity, and propose a novel approach to quantify it. We evaluate the quantification of fidelity in adversarial settings on two neural networks. The study shows that involving the fidelity enables a neural network system to detect adversarial examples with true positive rate 97.7%, and false positive rate 1.67% on a studied neural network.

Humans have created many pioneers of art from the beginning of time. There are not many notable achievements by an artificial intelligence to create something visually captivating in the field of art. However, some breakthroughs were made in the past few years by learning the differences between the content and style of an image using convolution neural networks and texture synthesis. But most of the approaches have the limitations on either processing time, choosing a certain style image or altering the weight ratio of style image. Therefore, we are to address these restrictions and provide a system which allows any style image selection with a user defined style weight ratio in minimum time possible.

The Moving Picture Experts Group's Compact Descriptors for Visual Search (MPEG's CDVS) intends to standardize technologies in order to enable an interoperable, efficient, and cross-platform solution for internet-scale visual search applications and services. Among the key technologies within CDVS, we recall the format of visual descriptors, the descriptor extraction process, and the algorithms for indexing and matching. Unfortunately, these steps require precision and computation accuracy. Moreover, they are very time-consuming, as they need running times in the order of seconds when implemented on the central processing unit (CPU) of modern mobile devices. In this paper, to reduce computation times and maintain precision and accuracy, we re-design, for many-cores embedded graphical processor units (GPUs), all main local descriptor extraction pipeline phases of the MPEG's CDVS standard. To reach this goal, we introduce new techniques to adapt the standard algorithm to parallel processing. Furthermore, to reduce memory accesses and efficiently distribute the kernel workload, we use new approaches to store and retrieve CDVS information on proper GPU data structures. We present a complete experimental analysis on a large and standard test set. Our experiments show that our GPU-based approach is remarkably faster than the CPU-based reference implementation of the standard, and it maintains a comparable precision in terms of true and false positive rates.

In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction. We present a meta-learning based policy gradient method for addressing the problem of adaptation in human-robot interaction and also investigate its role as a mechanism for trust modelling. By building an escape room scenario in mixed reality with a robot, we test our hypothesis that bi-directional trust can be influenced by different adaptation algorithms. We found that our proposed model increased the perceived trustworthiness of the robot and influenced the dynamics of gaining human's trust. Additionally, participants evaluated that the robot perceived them as more trustworthy during the interactions with the meta-learning based adaptation compared to the previously studied statistical adaptation model.