Biblio

With the continuous development of computer network technology, security problems in the network are emerging one after another, and it is becoming more and more difficult to ignore. For the current network administrators, how to successfully prevent malicious network hackers from invading, so that network systems and computers are at Safe and normal operation is an urgent task. This paper proposes a network intrusion detection method based on deep learning. This method uses deep confidence neural network to extract features of network monitoring data, and uses BP neural network as top level classifier to classify intrusion types. The method was validated using the KDD CUP'99 dataset from the Lincoln Laboratory of the Massachusetts Institute of Technology. The results show that the proposed method has a significant improvement over the traditional machine learning accuracy.

The recognition of intrusions has increased impressive enthusiasm for information mining with the acknowledgment that anomalies can be the key disclosure to be produced using extensive network databases. Intrusions emerge because of different reasons, for example, mechanical deficiencies, changes in framework conduct, fake conduct, human blunder and instrument mistake. Surely, for some applications the revelation of Intrusions prompts more intriguing and helpful outcomes than the disclosure of inliers. Discovery of anomalies can prompt recognizable proof of framework blames with the goal that executives can take preventive measures previously they heighten. A network database framework comprises of a sorted out posting of pages alongside programming to control the network information. This database framework has been intended to empower network operations, oversee accumulations of information, show scientific outcomes and to get to these information utilizing networks. It likewise empowers network clients to gather limitless measure of information on unbounded territories of utilization, break down it and return it into helpful data. Network databases are ordinarily used to help information control utilizing dynamic capacities on sites or for putting away area subordinate data. This database holds a surrogate for each network route. The formation of these surrogates is called ordering and each network database does this errand in an unexpected way. In this paper, a structure for compelling access control and Intrusion Detection using outliers has been proposed and used to give viable Security to network databases. The design of this framework comprises of two noteworthy subsystems to be specific, Access Control Subsystem and Intrusion Detection Subsystem. In this paper preprocessing module is considered which clarifies the preparing of preprocessing the accessible information. And rain forest method is discussed which is used for intrusion detection.

Internet is a widely used platform nowadays by people across the globe. This has led to the advancement in science and technology. Many surveys show that network intrusion has registered a consistent increase and lead to personal privacy theft and has become a major platform for attack in the recent years. Network intrusion is any unauthorized activity on a computer network. Hence there is a need to develop an effective intrusion detection system. In this paper we acquaint an intrusion detection system that uses improved genetic k-means algorithm(IGKM) to detect the type of intrusion. This paper also shows a comparison between an intrusion detection system that uses the k-means++ algorithm and an intrusion detection system that uses IGKM algorithm while using smaller subset of kdd-99 dataset with thousand instances and the KDD-99 dataset. The experiment shows that the intrusion detection that uses IGKM algorithm is more accurate when compared to k-means++ algorithm.

Aiming at the problem of node identification in wireless networks, a method of node identification based on deep learning is proposed, which starts with the tiny features of nodes in radiofrequency layer. Firstly, in order to cut down the computational complexity, Principal Component Analysis is used to reduce the dimension of node sample data. Secondly, a convolution neural network containing two hidden layers is designed to extract local features of the preprocessed data. Stochastic gradient descent method is used to optimize the parameters, and the Softmax Model is used to determine the output label. Finally, the effectiveness of the method is verified by experiments on practical wireless ad-hoc network.

In this paper we solve the problem of neural network technology development for e-mail messages classification. We analyze basic methods of spam filtering such as a sender IP-address analysis, spam messages repeats detection and the Bayesian filtering according to words. We offer the neural network technology for solving this problem because the neural networks are universal approximators and effective in addressing the problems of classification. Also, we offer the scheme of this technology for e-mail messages “spam”/“not spam” classification. The creation of effective neural network model of spam filtering is performed within the databases knowledge discovery technology. For this training set is formed, the neural network model is trained, its value and classifying ability are estimated. The experimental studies have shown that a developed artificial neural network model is adequate and it can be effectively used for the e-mail messages classification. Thus, in this paper we have shown the possibility of the effective neural network model use for the e-mail messages filtration and have shown a scheme of artificial neural network model use as a part of the e-mail spam filtering intellectual system.

This paper describes the technology of neural network application to solve the problem of information security incidents forecasting. We describe the general problem of analyzing and predicting time series in a graphical and mathematical setting. To solve this problem, it is proposed to use a neural network model. To solve the task of forecasting a time series of information security incidents, data are generated and described on the basis of which the neural network is trained. We offer a neural network structure, train the neural network, estimate it's adequacy and forecasting ability. We show the possibility of effective use of a neural network model as a part of an intelligent forecasting system.

Network situation value is an important index to measure network security. Establishing an effective network situation prediction model can prevent the occurrence of network security incidents, and plays an important role in network security protection. Through the understanding and analysis of the network security situation, we can see that there are many factors affecting the network security situation, and the relationship between these factors is complex., it is difficult to establish more accurate mathematical expressions to describe the network situation. Therefore, this paper uses the grey neural network as the prediction model, but because the convergence speed of the grey neural network is very fast, the network is easy to fall into local optimum, and the parameters can not be further modified, so the Multi-Swarm Chaotic Particle Optimization (MSCPO)is used to optimize the key parameters of the grey neural network. By establishing the nonlinear mapping relationship between the influencing factors and the network security situation, the network situation can be predicted and protected.

Major blackouts are due to cascading failures in power systems. These failures usually occur at vulnerable links of the network. To identify these, indicators have already been defined using complex network theory. However, most of these indicators only depend on the topology of the grid; they fail to detect the weak links. We introduce a new metric to identify the vulnerable lines, based on the load-flow equations and the grid geometry. Contrary to the topological indicators, ours is built from the electrical equations and considers the location and magnitude of the loads and of the power generators. We apply this new metric to the IEEE 118-bus system and compare its prediction of weak links to the ones given by an industrial software. The agreement is very well and shows that using our indicator a simple examination of the network and its generator and load distribution suffices to find the weak lines.

The numerical analysis of transient quantum effects in heterostructure devices with conventional numerical methods tends to pose problems. To overcome these limitations, a novel numerical scheme for the transient non-equilibrium solution of the quantum Liouville equation utilizing a finite volume discretization technique is proposed. Additionally, the solution with regard to the stationary regime, which can serve as a reference solution, is inherently included within the discretization scheme for the transient regime. Resulting in a highly oscillating interference pattern of the statistical density matrix as well in the stationary as in the transient regime, the reflecting nature of the conventional boundary conditions can be an additional source of error. Avoiding these non-physical reflections, the concept of a complex absorbing potential used for the Schrödinger equation is utilized to redefine the drift operator in order to render open boundary conditions for quantum transport equations. Furthermore, the method allows the application of the commonly used concept of inflow boundary conditions.

The class φ2 is a single transistor, fast transient inverter topology often associated with power conversion at very high frequency (VHF: 30MHz-300MHz). At VHF, gate drivers available on the market fail to provide the adequate transistor switching signal. Hence, there is a need for new power topologies that do no make use of gate drivers but are still suitable for power conversion at VHF. In This paper, we introduce a new class φ;2 topology that incorporates an oscillator, which takes the drain signal through a feedback circuit in order to force the transistor switching. A design methodology is provided and a 1MHz 20V input prototype is built in order to validate the topology behaviour.

HTTPS is gaining widespread popularity for secure transactions. Most popular sites have made default choice as HTTPS. This development of encrypted traffic has brought in new challenges in the areas of network security monitoring and analysis. This paper makes a survey through various study done in the area on novel approaches for identification and investigating HTTPS traffic and its effect on network security monitoring. This work makes a complete analysis and evaluation of HTTPS protocol-is it ensuring security or are we entering in a vicious cycle of finding weaknesses and tryingto fill the gaps in Network security Monitoring. There are couple of vacuums that exist along with encrypted data, namely firewalls, IDS becoming blind to data being exchanged, enhancing vulnerabilities by making it tough to implement security policy and probability of malicious activities hidingin the ciphered traffic. Most of the current techniques namely DPI to port based to IP address to DNS to SNI filtering is prone to be ineffective in front of HTTPS traffic. The emphasis is upon the new ways to explore the expanding HTTPS volume with security breaches to cover new challenges related to Network Security Monitoring. Data collected from couple of up to date research and their conclusion hasbeen discussed to provide a brief overview so as to provide the reader with an in-depth understanding of the research progress in thisarea.

Pervasive systems over the years continuous to grow exponentially. Engagement of IoT in fields such as Agriculture, Home automation, industrial applications etc is on the rise. Self organizing networks within the IoT field give rise to engagement of various nodes for data communication. The rise in Cyber-attacks within IoT pose a lot of threat to these connected nodes and hence there is a need for data passing through nodes to be verified during communication. In this paper we proposed a nodal authentication approach in IoT using blockchain in securing the integrity of data passing through the nodes in IoT. In our work, we engaged the GOST algorithm in our approach. At the end, we achieved a nodal authentication and verification of the transmitted data. This makes it very difficult for an attacker to fake a node in the communication chain of the connected nodes. Data integrity was achieved in the nodes during the communication.

In this work we present a novel technique for physical layer security in the Internet-of-Things (IoT) networks. In the proposed architecture, each IoT node generates a phase-modulated random key/data and transmits it to a master node in the presence of an eavesdropper, referred to as Eve. The master node, simultaneously, broadcasts a high power signal using an omni-directional antenna, which is received as interference by Eve. This interference masks the generated key by the IoT node and will result in a higher bit-error rate in the data received by Eve. The two legitimate intended nodes communicate in a full-duplex manner and, consequently, subtract their transmitted signals, as a known reference, from the received signal (self-interference cancellation). We compare our proposed method with a conventional approach to physical layer security based on directional antennas. In particular, we show, using theoretical and measurement results, that our proposed approach provides significantly better security measures, in terms bit error rate (BER) at Eve's location. Also, it is proven that in our novel system, the possible eavesdropping region, defined by the region with BER \textbackslashtextless; 10-1, is always smaller than the reliable communication region with BER \textbackslashtextless; 10-3.

The network coding optimization based on niche genetic algorithm can observably reduce the network overhead of encoding technology, however, security issues haven't been considered in the coding operation. In order to solve this problem, we propose a network coding optimization scheme for niche algorithm based on security performance (SNGA). It is on the basis of multi-target niche genetic algorithm(NGA)to construct a fitness function which with k-secure network coding mechanism, and to ensure the realization of information security and achieve the maximum transmission of the network. The simulation results show that SNGA can effectively improve the security of network coding, and ensure the running time and convergence speed of the optimal solution.

The applications in the critical infrastructure systems pose simultaneous resilience and performance requirements to the underlying computer network. To meet such requirements, the networks that use the store-and-forward paradigm poses stringent conditions on the redundancy in the network topology and results in problems that becoming computationally challenging to solve at scale. However, with the advent of programmable data-planes, it is now possible to use linear network coding (NC) at the intermediate network nodes to meet resilience requirements of the applications. To that end, we propose an architecture that realizes linear NC in programmable networks by decomposing the linear NC functions into the atomic coding primitives. We designed and implemented the primitives using the features offered by the P4 ecosystem. Using an empirical evaluation, we show that the theoretical gains promised by linear network coding can be realized with a per-packet processing cost.

In this research paper author surveys the need of data protection from intelligent systems in the private and public sectors. For this, she identifies that the Smart Information Security Intel processes needs to be the suggestive key policy for both sectors of governance either public or private. The information is very sensitive for any organization. When the government offices are concerned, information needs to be abstracted and encapsulated so that there is no information stealing. For this purposes, the art of skill set and new optimized technology needs to be stationed. Author identifies that digital bar-coded air port like security using conveyor belts and digital bar-coded conveyor boxes to scan switched ON articles like internet of things needs to be placed. As otherwise, there can potentially be data, articles or information stealing from the operational sites where access is unauthorized. Such activities shall need to be scrutinized, minutely. The biometric such as fingerprints, iris, voice and face recognition pattern updates in the virtual data tables must be taken to keep data entry-exit log up to-date. The information technicians of the sentinel systems must help catch the anomalies in the professional working time in private and public sectors if there is red flag as indicator. The author in this research paper shall discuss in detail what we shall station, how we shall station and what all measures we might need to undertake to safeguard the stealing of sensitive information from the organizations like administration buildings, government buildings, educational schools, hospitals, courts, private buildings, banks and all other offices nation-wide. The TO-BE new processes shall make the AS-IS office system more information secured, data protected and personnel security stronger.

A new quantum secret sharing protocol based on the ping-pong protocol of quantum secure direct communication is proposed. The pairs of entangled qutrits are used in protocol, which allows an increase in the information capacity compared with protocols based on entangled qubits. The detection of channel eavesdropping used in the protocol is being implemented in random moments of time, thereby it is possible do not use the significant amount of quantum memory. The security of the proposed protocol to attacks is considered. A method for additional amplification of the security to an eavesdropping attack in communication channels for the developed protocol is proposed.

With the developments in deep learning, the security of neural networks against vulnerabilities has become one of the most urgent research topics in deep learning. There are many types of security countermeasures. Adversarial examples and their defense methods, in particular, have been well-studied in recent years. An adversarial example is designed to make neural networks misclassify or produce inaccurate output. Audio adversarial examples are a type of adversarial example where the main target of attack is a speech-to-text transcription neural network. In this study, we propose a new defense method against audio adversarial examples for the speech-to-text transcription neural networks. It is difficult to determine whether an input waveform data representing the sound of voice is an audio adversarial example. Therefore, the main framework of the proposed defense method is based on a sandbox approach. To evaluate the proposed defense method, we used actual audio adversarial examples that were created on Deep Speech, which is a speech-to-text transcription neural network. We confirmed that our defense method can identify audio adversarial examples to protect speech-to-text systems.

As technology is developing exponentially and the world is moving towards automation, the resources have to be transferred through the internet which requires routers to connect networks and forward bundles (information). Due to the vulnerability of routers the data and resources have been hacked. The vulnerability of routers is due to minimum authentication to the network shared, some technical attacks on routers, leaking of passwords to others, single passwords. Based on the study, the solution is to maximize authentication of the router by embedding an application that monitors the user entry based on MAC address of the device, the password is frequently changed and that encrypted password is sent to a user and notifies the admin about the changes. Thus, these routers provide high-level security to the forward data through the internet.

In this paper, we propose a novel PHY layer security technique in radio frequency identification (RFID) backscatter communications system. In order to protect the RFID tag information confidentiality from the eavesdroppers attacks, the proposed technique deploys beam steering (BS) using a one dimensional (1-D) antenna array in the tag side in addition to noise injection from the reader side. The performance analysis and simulation results show that the new technique outperforms the already-existing noise injection security technique and overcomes its design limitations.

Random numbers are important tools for generating secret keys, encrypting messages, or masking the content of certain protocols with a random sequence that can be deterministically generated. The lack of assurance about the random numbers generated can cause serious damage to cryptographic protocols, prompting vulnerabilities to be exploited by the attackers. In this paper, a new pseudo - random number generator algorithm that uses dynamic system clock converted to Epoch Timestamp as PRNG seed was developed. The algorithm uses a Linear Congruential Generator (LCG) algorithm that produces a sequence of pseudo - randomized numbers that performs mathematical operations to transform numbers that appears to be unrelated to the Seed. Simulation result shows that the new PRNG algorithm does not generate repeated random numbers based on the frequency of iteration, a good indicator that the key for random numbers is secured. Numerical analysis using NIST Test Suite results concerning to random sequences generated random numbers has a total average of 0.342 P-value. For a p-value ≥ 0.001, a sequence would be considered to be random with a confidence of 99.9%. This shows that robustness and unpredictability were achieved. Hence, It is highly deterministic in nature and has a good quality of Pseudo-Random Numbers. It is therefore a good source of a session key generation for encryption, reciprocal in the authentication schemes and other cryptographic algorithm parameters that improve and secure data from any type of security attack.

The biggest challenge of sharing data stored in cloud-storage is privacy-preservation. In this paper, we propose a simple yet effective solution for enforcing the security of private data stored in some cloud storage for sharing. We consider an environment where even if the cloud service provider is not-reliable or is compromised, our data still remain secure. The data Owner encrypts the private files using a secret key, file identifier and hash function and then uploads the cipher text files to the cloud. When a Data user requests access to a file, the owner establishes a key with the user and creates a new key, which is sent to the user. The user can then extract the original key by using the mutually established secret key and use it to decrypt the encrypted file. Thus we propose a system which is computationally simple yet provides a secure mechanism for sharing private data even over an untrusted cloud service provider.

With the increasing prevalence of mobile devices, face-to-face device-to-device (D2D) communication has been applied to a variety of daily scenarios such as mobile payment and short distance file transfer. In D2D communications, a critical security problem is verifying the legitimacy of devices when they share no secrets in advance. Previous research addressed the problem with device authentication and pairing schemes based on user intervention or exploiting physical properties of the radio or acoustic channels. However, a remaining challenge is to secure face-to-face D2D communication even in the middle of a crowd, within which an attacker may hide. In this paper, we present Nhuth, a nonlinearity-enhanced, location-sensitive authentication mechanism for such communication. Especially, we target at the secure authentication within a limited range such as 20 cm, which is the common case for face-to-face scenarios. Nhuth contains averification scheme based on the nonlinear distortion of speaker-microphone systems and a location-based-validation model. The verification scheme guarantees device authentication consistency by extracting acoustic nonlinearity patterns (ANP) while the validation model ensures device legitimacy by measuring the time difference of arrival (TDOA) at two microphones. We analyze the security of Nhuth theoretically and evaluate its performance experimentally. Results show that Nhuth can verify the device legitimacy in the presence of nearby attackers.

With the rising popularity of file-sharing services such as Google Drive and Dropbox in the workflows of individuals and corporations alike, the protection of client-outsourced data from unauthorized access or tampering remains a major security concern. Existing cryptographic solutions to this problem typically require server-side support, involve non-trivial key management on the part of users, and suffer from severe re-encryption penalties upon access revocations. This combination of performance overheads and management burdens makes this class of solutions undesirable in situations where performant, platform-agnostic, dynamic sharing of user content is required. We present NEXUS, a stackable filesystem that leverages trusted hardware to provide confidentiality and integrity for user files stored on untrusted platforms. NEXUS is explicitly designed to balance security, portability, and performance: it supports dynamic sharing of protected volumes on any platform exposing a file access API without requiring server-side support, enables the use of fine-grained access control policies to allow for selective sharing, and avoids the key revocation and file re-encryption overheads associated with other cryptographic approaches to access control. This combination of features is made possible by the use of a client-side Intel SGX enclave that is used to protect and share NEXUS volumes, ensuring that cryptographic keys never leave enclave memory and obviating the need to reencrypt files upon revocation of access rights. We implemented a NEXUS prototype that runs on top of the AFS filesystem and show that it incurs ×2 overhead for a variety of common file and database operations.

Blackboxes are being increasingly used in the vehicular context to store and transmit information related to safety, security and many other applications. The plethora of sensors available at the different parts of the vehicle can provide enriched gathering of the data related to these applications. Nonetheless, to support multiple use cases, the blackbox must be accessible by various actors (e.g. vehicle owner, insurance company, law enforcement authorities). This raises significant challenges regarding the privacy of the data collected and stored in the blackbox. In fact, these data can often lead to tracing back accurate facts about the behaviour of the owner of the vehicle. To cope with this problem, we propose a new blackbox architecture supporting searchable encryption. This feature allows multiple users who are not able to decipher the content of the blackbox to validate properties such as path traceback and velocity. To illustrate the implementation of the proposed technique in practice, we discuss a case study related to post-accident processing by insurance companies.