Biblio

Volume, Variety, Velocity, Veracity & Value of data has drawn the attention of many analysts in the last few years. Performance optimization and comparison are the main challenges we face when we talk about the humongous volume of data. Data Analysts use data for activities like forecasting or deep learning and to process these data various tools are available which helps to achieve this task with minimum efforts. Recommendation System plays a crucial role while running any business such as a shopping website or travel agency where the system recommends the user according to their search history, likes, comments, or their past order/booking details. Recommendation System works on various strategies such as Content Filtering, Collaborative Filtering, Neighborhood Methods, or Matrix Factorization methods. For achieving maximum efficiency and accuracy based on the data a specific strategy can be the best case or the worst case for that scenario. Matrix Factorization is the key point of interest in this work. Matrix Factorization strategy includes multiplication of user matrix and item matrix in-order to get a rating matrix that can be recommended to the users. Matrix Multiplication can be achieved by using various algorithms such as Naive Algorithm, Strassen Algorithm, Coppersmith - Winograd (CW) Algorithm. In this work, a new algorithm is proposed to achieve less amount of time and space complexity used in-order for performing matrix multiplication which helps to get the results much faster. By using the Matrix Factorization strategy with various Matrix Multiplication Algorithm we are going to perform a comparative analysis of the same to conclude the proposed algorithm is more efficient.

With the development of positioning technology and the popularity of mobile devices, location-based services have been widely deployed. To use the services, users must provide the server accurate location information, during which the attacker tends to infer sensitive information from intercepting queries. In this paper, we model the road network as an edge cluster graph with its location semantics considered. Then, we propose the Circle First Structure Optimization (CFSO) algorithm which generates an anonymous set by adding optimal adjacent locations. Furthermore, we introduce controllable randomness and propose the Attack-Resilient (AR) algorithm to enhance the anti-attack ability. Meanwhile, to reduce the system overhead, our algorithms build the anonymous set quickly and take the structure of the anonymous set into account. Finally, we conduct experiments on a real map and the results demonstrate a higher anonymity success rate and a stronger anti-attack capability with less system overhead.

The increased reliance on the Internet and the corresponding surge in connectivity demand has led to a significant growth in Internet-of-Things (IoT) devices. The continued deployment of IoT devices has in turn led to an increase in network attacks due to the larger number of potential attack surfaces as illustrated by the recent reports that IoT malware attacks increased by 215.7% from 10.3 million in 2017 to 32.7 million in 2018. This illustrates the increased vulnerability and susceptibility of IoT devices and networks. Therefore, there is a need for proper effective and efficient attack detection and mitigation techniques in such environments. Machine learning (ML) has emerged as one potential solution due to the abundance of data generated and available for IoT devices and networks. Hence, they have significant potential to be adopted for intrusion detection for IoT environments. To that end, this paper proposes an optimized ML-based framework consisting of a combination of Bayesian optimization Gaussian Process (BO-GP) algorithm and decision tree (DT) classification model to detect attacks on IoT devices in an effective and efficient manner. The performance of the proposed framework is evaluated using the Bot-IoT-2018 dataset. Experimental results show that the proposed optimized framework has a high detection accuracy, precision, recall, and F-score, highlighting its effectiveness and robustness for the detection of botnet attacks in IoT environments.

The development of control systems of increased reliability is highly relevant due to their widespread introduction in various sectors of human activity, including those where failure of the control system can lead to serious or catastrophic consequences. The increase of the reliability of control systems is directly related with the reliability of control computers (so called intellectual centers) since the computer technology is the basis of modern control systems. One of the possible solutions to the development of highly reliable control computers is the practical implementation of the provisions of the theory of structural stability, which involves the practical solution of two main tasks - this is the task of functional adaptation and the preceding task of functional diagnostics. This article deals with the issues on the assessment of computational complexity of the implementation of the adaptation process of structural and sustainable control computer. The criteria of computational complexity are the characteristics of additionally attracted resources, such as the temporal characteristics of the adaptation process and the characteristics of the involved amount of memory resources of the control computer involved in the implementation of the adaptation process algorithms.

Traditional attributed network embedding methods are designed to map structural and attribute information of networks jointly into a continuous Euclidean space, while recently a novel branch of them named binarized attributed network embedding has emerged to learn binary codes in Hamming space, aiming to save time and memory costs and to naturally fit node retrieval task. However, current binarized attributed network embedding methods are scarce and mostly ignore the local attribute similarity between each pair of nodes. Besides, none of them attempt to control the independency of each dimension(bit) of the learned binary representation vectors. As existing methods still need improving, we propose an unsupervised Neural-based Binarized Attributed Network Embedding (NBANE) approach. Firstly, we inherit the Weisfeiler-Lehman proximity matrix from predecessors to aggregate high-order features for each node. Secondly, we feed the aggregated features into an autoencoder with the attribute similarity penalizing term and the orthogonality term to make further dimension reduction. To solve the problem of integer optimization we adopt the relaxation-quantization method during the process of training neural networks. Empirically, we evaluate the performance of NBANE through node classification and clustering tasks on three real-world datasets and study a case on fast retrieval in academic networks. Our method achieves better performance over state- of-the-art baselines methods of various types.

YARA rules utilises string or pattern matching to perform malware analysis and is one of the most effective methods in use today. However, its effectiveness is dependent on the quality and quantity of YARA rules employed in the analysis. This can be managed through the rule optimisation process, although, this may not necessarily guarantee effective utilisation of YARA rules and its generated findings during its execution phase, as the main focus of YARA rules is in determining whether to trigger a rule or not, for a suspect sample after examining its rule condition. YARA rule conditions are Boolean expressions, mostly focused on the binary outcome of the malware analysis, which may limit the optimised use of YARA rules and its findings despite generating significant information during the execution phase. Therefore, this paper proposes embedding fuzzy rules with YARA rules to optimise its performance during the execution phase. Fuzzy rules can manage imprecise and incomplete data and encompass a broad range of conditions, which may not be possible in Boolean logic. This embedding may be more advantageous when the YARA rules become more complex, resulting in multiple complex conditions, which may not be processed efficiently utilising Boolean expressions alone, thus compromising effective decision-making. This proposed embedded approach is applied on a collected malware corpus and is tested against the standard and enhanced YARA rules to demonstrate its success.

We address energy-efficient placement of data and analytics components of composite analytics services on a wireless network to minimize execution-time energy consumption (computation and communication) subject to compute, storage and network resource constraints. We introduce an expressive analytics service hypergraph model for representing k-ary composability relationships (k ≥ 2) between various analytics and data components and leverage binary quadratic programming (BQP) to minimize the total energy consumption of a given placement of the analytics hypergraph nodes on the network subject to resource availability constraints. Then, after defining a potential energy functional Φ(·) to model the affinities of analytics components and network resources using analogs of attractive and repulsive forces in physics, we propose a decentralized Metropolis Monte Carlo (MMC) sampling method which seeks to minimize Φ by moving analytics and data on the network. Although Φ is non-convex, using a potential game formulation, we identify conditions under which the algorithm provably converges to a local minimum energy equilibrium placement configuration. Trace-based simulations of the placement of a deep-neural-network analytics service on a realistic wireless network show that for smaller problem instances our MMC algorithm yields placements with total energy within a small factor of BQP and more balanced workload distributions; for larger problems, it yields low-energy configurations while the BQP approach fails.

In this thesis, an modified algorithm for grey wolf optimization in swarm intelligence optimization algorithm is proposed, which is called an adaptive grey wolf algorithm (AdGWO) based on population system and bacterial foraging optimization algorithm (BFO). In view of the disadvantages of premature convergence and local optimization in solving complex optimization problems, the AdGWO algorithm uses a three-stage nonlinear change function to simulate the decreasing change of the convergence factor, and at the same time integrates the half elimination mechanism of the BFO. These improvements are more in line with the actual situation of natural wolves. The algorithm is based on 23 famous test functions and compared with GWO. Experimental results demonstrate that this algorithm is able to avoid sinking into the local optimum, has good accuracy and stability, is a more competitive algorithm.

For real-time applications of arbitrary style transformation, there is a trade-off between the quality of results and the running time of existing algorithms. Hence, it is required to maintain the equilibrium of the quality of generated artwork with the speed of execution. It's complicated for the present arbitrary style-transformation procedures to preserve the structure of content-image while blending with the design and pattern of style-image. This paper presents the implementation of a network using SANET models for generating impressive artworks. It is flexible in the fusion of new style characteristics while sustaining the semantic-structure of the content-image. The identity-loss function helps to minimize the overall loss and conserves the spatial-arrangement of content. The results demonstrate that this method is practically efficient, and therefore it can be employed for real-time fusion and transformation using arbitrary styles.

It is now possible to synthesize highly realistic images of people who do not exist. Such content has, for example, been implicated in the creation of fraudulent socialmedia profiles responsible for dis-information campaigns. Significant efforts are, therefore, being deployed to detect synthetically-generated content. One popular forensic approach trains a neural network to distinguish real from synthetic content.We show that such forensic classifiers are vulnerable to a range of attacks that reduce the classifier to near- 0% accuracy. We develop five attack case studies on a state- of-the-art classifier that achieves an area under the ROC curve (AUC) of 0.95 on almost all existing image generators, when only trained on one generator. With full access to the classifier, we can flip the lowest bit of each pixel in an image to reduce the classifier's AUC to 0.0005; perturb 1% of the image area to reduce the classifier's AUC to 0.08; or add a single noise pattern in the synthesizer's latent space to reduce the classifier's AUC to 0.17. We also develop a black-box attack that, with no access to the target classifier, reduces the AUC to 0.22. These attacks reveal significant vulnerabilities of certain image-forensic classifiers.

For solving multi-objective optimization problems, this paper firstly combines a multi-objective evolutionary algorithm based on decomposition (MOEA/D) with good convergence and non-dominated sorting genetic algorithm II (NSGA-II) with good distribution to construct. Thus we propose a hybrid multi-objective optimization solving algorithm. Then, we consider that the population diversity needs to be improved while applying multi-objective particle swarm optimization (MOPSO) to solve the multi-objective optimization problems and an improved MOPSO algorithm is proposed. We give the distance function between the individual and the population, and the individual with the largest distance is selected as the global optimal individual to maintain population diversity. Finally, the simulation experiments are performed on the ZDT\textbackslashtextbackslashDTLZ test functions and track planning problems. The results indicate the better performance of the improved algorithms.

Packet classification is used to determine the behavior of incoming packets to network devices. Because it is achieved using a linear search on a classification rule list, a larger number of rules leads to a longer communication latency. To decrease this latency, the problem is generalized as Optimal Rule Ordering (ORO), which aims to identify the order of rules that minimizes the classification latency caused by packet classification while preserving the classification policy. Because ORO is known to be NP-complete by Hamed and Al-Shaer [Dynamic rule-ordering optimization for high-speed firewall filtering, ASIACCS (2006) 332-342], various heuristics for ORO have been proposed. Sub-graph merging (SGM) by Tapdiya and Fulp [Towards optimal firewall rule ordering utilizing directed acyclical graphs, ICCCN (2009) 1-6] is the state of the art heuristic algorithm for ORO. In this paper, we propose a novel heuristic method for ORO. Although most heuristics try to recursively determine the maximum-weight rule and move it as far as possible to an upper position, our algorithm pairs rules that cause policy violations until there are no such rules to simply sort the rules by these weights. Our algorithm markedly decreases the classification latency and reordering time compared with SGM in experiments. The sets consisting of thousands of rules that require one or more hours for reordering by SGM can be reordered by the proposed method within one minute.

Following substantial advancements in stochastic classes of decision-making optimization problems, scenario-based stochastic optimization, robust\textbackslashtextbackslash distributionally robust optimization, and chance-constrained optimization have recently gained an increasing attention. Despite the remarkable developments in probabilistic forecast of uncertainties (e.g., in renewable energies), most approaches are still being employed in a univariate framework which fails to unlock a full understanding on the underlying interdependence among uncertain variables of interest. In order to yield cost-optimal solutions with predefined probabilistic guarantees, conditional and dynamic interdependence in uncertainty forecasts should be accommodated in power systems decision-making. This becomes even more important during the emergencies where high-impact low-probability (HILP) disasters result in remarkable fluctuations in the uncertain variables. In order to model the interdependence correlation structure between different sources of uncertainty in power systems during both normal and emergency operating conditions, this paper aims to bridge the gap between the probabilistic forecasting methods and advanced optimization paradigms; in particular, perdition regions are generated in the form of ellipsoids with probabilistic guarantees. We employ a modified Khachiyan's algorithm to compute the minimum volume enclosing ellipsoids (MVEE). Application results based on two datasets on wind and photovoltaic power are used to verify the efficiency of the proposed framework.

This work considers the trade-off between security and performance when revealing partial information about encrypted data computed on. The focus of our work is on information revealed through control flow side-channels when executing programs on encrypted data. We use quantitative information flow to measure security, running time to measure performance and program transformation techniques to alter the trade-off between the two. Combined with information flow policies, we perform a policy-aware security and performance trade-off (PASAPTO) analysis. We formalize the problem of PASAPTO analysis as an optimization problem, prove the NP-hardness of the corresponding decision problem and present two algorithms solving it heuristically. We implemented our algorithms and combined them with the Dataflow Authentication (DFAuth) approach for outsourcing sensitive computations. Our DFAuth Trade-off Analyzer (DFATA) takes Java Bytecode operating on plaintext data and an associated information flow policy as input. It outputs semantically equivalent program variants operating on encrypted data which are policy-compliant and approximately Pareto-optimal with respect to leakage and performance. We evaluated DFATA in a commercial cloud environment using Java programs, e.g., a decision tree program performing machine learning on medical data. The decision tree variant with the worst performance is 357% slower than the fastest variant. Leakage varies between 0% and 17% of the input.

With increasing improvements in different areas, Internet control has been making prominent impacts in almost all areas of technology that has resulted in reasonable advances in every discrete field and therefore the industries too are proceeding to the field of IoT (Internet of Things), in which the communication among heterogeneous equipments is via Internet broadly. So imparting these advances of technology in the Power Station Plant sectors i.e. the power plants will be remotely controlled additional to remote monitoring, with no corporal place as a factor for controlling or monitoring. But imparting this technology the security factor needs to be considered as a basic and such methods need to be put into practice that the communication in such networks or control systems is defended against any third party interventions while the data is being transferred from one device to the other device through the internet (Unrestricted Channel). The paper puts forward exercising RSA,DES and AES encrypting schemes for the purpose of data encryption at the Data Link Layer i.e. before it is transmitted to the other device through Internet and as a result of this the security constraints are maintained. The records put to use have been supplied by NTPC, Dadri, India plus simulation part was executed employing MATLAB.

Passive radio frequency identification (RFID) systems raise new transmission secrecy protection challenges against the special proactive eavesdropper, since it is able to both enhance the information wiretap and interfere with the information detection at the RFID reader simultaneously by broadcasting its own continuous wave (CW) signal. To defend against proactive eavesdropping attacks, we propose an artificial noise (AN) aided secure transmission scheme for the RFID reader, which superimposes an AN signal on the CW signal to confuse the proactive eavesdropper. The power allocation between the AN signal and the CW signal are optimized to maximize the secrecy rate. Furthermore, we model the attack and defense process between the proactive eavesdropper and the RFID reader as a hierarchical security game, and prove it can achieve the equilibrium. Simulation results show the superiority of our proposed scheme in terms of the secrecy rate and the interactions between the RFID reader and the proactive eavesdropper.

The wireless communication is a backbone for a development of a nation. But spectrum is finite resource and issues like spectrum scarcity, loss of signal quality, transmission delay, raised in wireless communication system due to growth of wireless applications and exponentially increased number of users. Secondary use of a spectrum using Software Defined Radio (SDR) is one of the solutions which is also supported by TRAI. The spectrum sensing is key process in communication based on secondary use of spectrum. But energy consumption, added delay, primary users security are some threats in this system. Here in this paper we mainly focused on throughput optimization in secondary use of spectrum based on optimal sensing time and number of Secondary users during cooperative spectrum sensing in Cognitive radio networks.

This paper discusses formulations and algorithms which allow a number of agents to collectively solve problems involving both (non-convex) minimization and (concave) maximization operations. These problems have a number of interesting applications in information processing and machine learning, and in particular can be used to model an adversary learning problem called network data poisoning. We develop a number of algorithms to efficiently solve these non-convex min-max optimization problems, by combining techniques such as gradient tracking in the decentralized optimization literature and gradient descent-ascent schemes in the min-max optimization literature. Also, we establish convergence to a first order stationary point under certain conditions. Finally, we perform experiments to demonstrate that the proposed algorithms are effective in the data poisoning attack.

This work introduces methods that unlock a series of applications for decision trees and neural networks in power system optimization. Capturing constraints that were impossible to capture before in a scalable way, we use decision trees (or neural networks) to extract an accurate representation of the non-convex feasible region which is characterized by both algebraic and differential equations. Applying an exact transformation, we convert the information encoded in the decision trees and the neural networks to linear decision rules that we incorporate as conditional constraints in an optimization problem (MILP or MISOCP). Our approach introduces a framework to unify security considerations with electricity market operations, capturing not only steady-state but also dynamic stability constraints in power system optimization, and has the potential to eliminate redispatching costs, leading to savings of millions of euros per year.

Antisparse coding aims at spreading the information uniformly over representation coefficients and can be expressed as the solution of an ℓ∞-norm regularized problem. In this paper, we propose a new methodology, coined "safe squeezing", accelerating the computation of antisparse representations. The idea consists in identifying saturated entries of the solution via simple tests and compacting their contribution to achieve some form of dimensionality reduction. Numerical experiments show that the proposed approach leads to significant computational gain.

Smart meters (SMs) can pose privacy threats for consumers, an issue that has received significant attention in recent years. This paper studies the impact of Side Information (SI) on the performance of possible attacks to real-time privacy-preserving algorithms for SMs. In particular, we consider a deep adversarial learning framework, in which the desired releaser, which is a Recurrent Neural Network (RNN), is trained by fighting against an adversary network until convergence. To define the objective for training, two different approaches are considered: the Causal Adversarial Learning (CAL) and the Directed Information (DI)-based learning. The main difference between these approaches relies on how the privacy term is measured during the training process. The releaser in the CAL method, disposing of supervision from the actual values of the private variables and feedback from the adversary performance, tries to minimize the adversary log-likelihood. On the other hand, the releaser in the DI approach completely relies on the feedback received from the adversary and is optimized to maximize its uncertainty. The performance of these two algorithms is evaluated empirically using real-world SMs data, considering an attacker with access to SI (e.g., the day of the week) that tries to infer the occupancy status from the released SMs data. The results show that, although they perform similarly when the attacker does not exploit the SI, in general, the CAL method is less sensitive to the inclusion of SI. However, in both cases, privacy levels are significantly affected, particularly when multiple sources of SI are included.

As a promising solution of spectrum shortage, spectrum sharing has received tremendous interests recently. However, under different sharing policies of different licensees, the shared spectrum is heterogeneous both temporally and spatially, and is usually uncertain due to the unpredictable activities of incumbent users. In this paper, considering the spectrum uncertainty, we propose a spectrum sharing based delay-tolerant traffic off-loading (SDTO) scheme. To capture the available heterogeneous shared bands, we adopt a mesh cognitive radio network and employ the multi-hop transmission mode. To statistically guarantee the end-to-end (E2E) session request under the uncertain spectrum supply, we formulate the SDTO scheme into a stochastic optimization problem, which is transformed into a mixed integer nonlinear programming (MINLP) problem. Then, a coarse-fine search based iterative heuristic algorithm is proposed to solve the MINLP problem. Simulation results demonstrate that the proposed SDTO scheme can well schedule the network resource with an E2E session guarantee.

Underwater Acoustic Sensor Networks (UASNs) are often deployed in hostile environments, and they face many security threats. Moreover, due to the harsh characteristics of the underwater environment, UASNs are vulnerable to malicious attacks. One of the most dangerous security threats is the eavesdropping attack, where an adversary silently collects the information exchanged between the sensor nodes. Although careful assignment of transmission power levels and optimization of data flow paths help alleviate the extent of eavesdropping attacks, the network lifetime can be negatively affected since routing could be established using sub-optimal paths in terms of energy efficiency. In this work, two optimization models are proposed where the first model minimizes the potential eavesdropping risks in the network while the second model maximizes the network lifetime under a certain level of an eavesdropping risk. The results show that network lifetimes obtained when the eavesdropping risks are minimized significantly shorter than the network lifetimes obtained without considering any eavesdropping risks. Furthermore, as the countermeasures against the eavesdropping risks are relaxed, UASN lifetime is shown to be prolonged, significantly.

The number of Mobile device users in the word has evolved rapidly. Many internet users currently want to connect the internet for all utilities automatically. One of the technologies in the IPv6 network, which supports data access from moving users, is IPv6 Mobile protocol. In its mobility, the users on a range of networks can move the range to another network. High demand for this technology will interest to a hacker or a cracker to carry out an attack. One of them is a DoS attack that compromises a target to denial its services. A firewall is usually used to protect networks from external attacks. However, since the firewall based on the attacker database, the unknown may not be detected. In order to address the obstacle, a detection tool could be used. In this research, IDS as an intrusion detection tool was integrated with a firewall to be implemented in IPv6 Mobile to stop the DoS attack. The results of some experiments showed that the integration system could block the attack at 0.9 s in Correspondent Node and 1.2 s in Home Agent. The blocked attack can decrease the network throughput up to 27.44% when a Mobile Node in Home Agent, 28,87% when the Mobile Node in a Foreign Network. The final result of the blocked attack is reducing the average CPU utilization up to 30.99%.

Advanced Persistent Threats (APTs) refer to sophisticated, prolonged and multi-step attacks, planned and executed by skilled adversaries targeting government and enterprise networks. Attack graphs' topologies can be leveraged to detect, explain and visualize the progress of such attacks. However, due to the abundance of false-positives, such graphs are usually overwhelmingly large and difficult for an analyst to understand. Graph partitioning refers to the problem of reducing the graph of alerts to a set of smaller incidents that are easier for an analyst to process and better represent the actual attack plan. Existing approaches are oblivious to the security-context of the problem at hand and result in graphs which, while smaller, make little sense from a security perspective. In this paper, we propose an optimization approach allowing us to generate security-aware partitions, utilizing aspects such as the kill chain progression, number of assets involved, as well as the size of the graph. Using real-world datasets, the results show that our approach produces graphs that are better at capturing the underlying attack compared to state-of-the-art approaches and are easier for the analyst to understand.