检索结果-内蒙古大学图书馆

Data Leakage Prevention for Data in Transit using Artificial Intelligence and Encryption Techniques 6

学校读者我要写书评

暂无评论

Data Leakage Prevention for Data in Transit using Artificial...

6th IEEE International Conference on Advances in Computing, Communication and Control, ICAC3 2019

作者： Ghouse, Mohammed Nene, Manisha J. VembuSelvi, C. DM Network and Cyber Security Bharat Electronics Limited Bangalore India Defense Institute of Advanced Technology Dept. of Computer Science and Engineering Pune India MRS Cyber Security Central Research Laboratory BEL Bangalore India

ISBN: (纸本)9781728123868

Data leakage in an organization is a very important concern that leads to the ex-filtration of data, The work in this paper addresses a novel concept for prevention of data leakage for data in transit. The text under consideration is classified to confidential or non-confidential category based on the content and context using Machine Learning technique. Subsequent action for encryption is performed on the confidential data and then transmitted from the Intranet domain to Internet domain ensuring that the data is not compromised to unauthorized users. In addition, normal transactional data which is nonconfidential in nature is not prevented from transmitting and is easily accessible by a third party. Encryption is applied only to selected data and not the entire data in transit, ensuring that the hardware resources are efficiently utilized. An adversary can simply compose an e-mail with the organization's confidential information as the body of the mail, in such scenarios our method will classify the e-mail content and will encrypt the data so that the data is not revealed to an outsider. © 2019 IEEE.

关键词： Cryptography

Efficient Context-aware File System Approach

学校读者我要写书评

暂无评论

Efficient Context-aware File System Approach

International Conference on Software Defined systems (SDS)

作者： Abdul Razaque Fathi Amsaad Muder Almiani Wan Xiaoya Li Shiyu Raouf Ganda Majdi Rawashdeh Amer AlRahayfeh Dept. of Computer Engineering and Telecommunication School of Information Security Eastern Michigan University US College of Information Technology Al-Hussein Bin Talal University Jordan Dept. of Computer Science NYIT Nanjing China Yale School of Management Yale University USA Department of Business Information Technology Princess Sumaya University for Technology Amman Jordan

ISBN: (数字)9781728172194

ISBN: (纸本)9781728172200

With the rapid development of science and technology, wireless networks are now widely used throughout the world. Given the requirement to improve the usability of computers, a context-aware file system has been rendered as an important research topic. Enhanced methods must be proposed to improve the accuracy of user authority in such systems. In this study, we introduce a combined approach involving the historical and physical user contexts to gain the contextual information for the file system. We proposed a role-based access control (RBAC) based on context awareness model, which is an extension of the traditional RBAC model, to implement context awareness in the users' permission for the file system. Using the context constraints, the file system can control the access of the user to protect the file system from damages caused by hackers. Results showed that the proposed method is more accurate than traditional ones because it can control the user access through context awareness.

关键词： File systems Context modeling Context-aware services Heuristic algorithms Object recognition Error analysis

WaveTTS: Tacotron-based TTS with joint time-frequency domain loss

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Rui Sisman, Berrak Bao, Feilong Gao, Guanglai Li, Haizhou Inner Mongolia University China Dept. of Electrical and Computer Engineering National University of Singapore Singapore Information Systems Technology and Design Singapore University of Technology and Design Singapore

Tacotron-based text-to-speech (TTS) systems directly synthesize speech from text input. Such frameworks typically consist of a feature prediction network that maps character sequences to frequency-domain acoustic features, followed by a waveform reconstruction algorithm or a neural vocoder that generates the time-domain waveform from acoustic features. As the loss function is usually calculated only for frequency-domain acoustic features, that doesn’t directly control the quality of the generated time-domain waveform. To address this problem, we propose a new training scheme for Tacotron-based TTS, referred to as WaveTTS, that has 2 loss functions: 1) time-domain loss, denoted as the waveform loss, that measures the distortion between the natural and generated waveform;and 2) frequency-domain loss, that measures the Mel-scale acoustic feature loss between the natural and generated acoustic features. WaveTTS ensures both the quality of the acoustic features and the resulting speech waveform. To our best knowledge, this is the first implementation of Tacotron with joint time-frequency domain loss. Experimental results show that the proposed framework outperforms the baselines and achieves high-quality synthesized speech. Copyright © 2020, The Authors. All rights reserved.

关键词： Frequency domain analysis

A Research on the Vulnerabilities of PLC using Search Engine

学校读者我要写书评

暂无评论

A Research on the Vulnerabilities of PLC using Search Engine

International Conference on information and Communication Technology Convergence (ICTC)

作者： Thummim Lee Sangwon Kim Keechoen Kim Dept. of IT congervence security Konkuk Univ. Seoul Korea Dept. of Computer Information & Communications Engineering Konkuk Univ. Seoul Korea Dept. of Computer Science & Engineering Konkuk Univ. Seoul Korea

The development and convergence of information and communication technologies have been leading to various studies on big data, artificial intelligence, internet of things, and smart cars to be introduced to our daily life. Especially, Smart factory which also base on ICT technology mentioned above are gradually applied to automation of intelligent manufacturing processes which is used to take place in a factory to drive down manufacturing costs and time to profit. Like governments that already encourage the introduction of smart factories, individuals and organizations are also considering introduction of smart factories. Smart factory requires modbus protocol to communicate and it must come with ICS, SCADA, PLC. These systems are greatly important in terms of security. However, using some of public website like Shodan makes it possible to search easily networks related to critical systems and devices. For safe and secure operation in smart factory, we need to raise awareness to these kind of security vulnerabilities in the ICS so that smart factories can cope with security accidents that might occur. In addition, for successfully introduction and activation of smart factories, security vulnerabilities must be reduced by using security measures and security devices should be applied for the ICS. As a baseline work for security improvement, we arrange the potential security vulnerabilities by conducting various real-world experiments and propose some security measures. Through this research, we expect to encourage security awareness of using smart factories which are undoubtedly important issue.

关键词： security Integrated circuits Smart manufacturing Protocols Control systems IP networks Uninterruptible power systems

Extending signature-based intrusion detection systems with Bayesian abductive reasoning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ganesan, Ashwinkumar Parameshwarappa, Pooja Peshave, Akshay Chen, Zhiyuan Oates, Tim Dept. of Computer Science & Electrical Engineering UMBC Maryland United States Dept. Of Information Systems UMBC Maryland United States

Evolving cybersecurity threats are a persistent challenge for system administrators and security experts as new malwares are continually released. Attackers may look for vulnerabilities in commercial products or execute sophisticated reconnaissance campaigns to understand a target's network and gather information on security products like firewalls and intrusion detection / prevention systems (network or host-based). Many new attacks tend to be modifications of existing ones. In such a scenario, rule-based systems fail to detect the attack, even though there are minor differences in conditions / attributes between rules to identify the new and existing attack. To detect these differences the IDS must be able to isolate the subset of conditions that are true and predict the likely conditions (different from the original) that must be observed. In this paper, we propose a probabilistic abductive reasoning approach that augments an existing rule-based IDS (snort [29]) to detect these evolved attacks by (a) Predicting rule conditions that are likely to occur (based on existing rules) and (b) able to generate new snort rules when provided with seed rule (i.e. a starting rule) to reduce the burden on experts to constantly update them. We demonstrate the effectiveness of the approach by generating new rules from the snort 2012 rules set and testing it on the MACCDC 2012 dataset [6]. Copyright © 2019, The Authors. All rights reserved.

关键词： Bayesian networks

FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Reisizadeh, Amirhossein Mokhtari, Aryan Hassani, Hamed Jadbabaie, Ali Pedarsani, Ramtin Dept. of Electrical & Computer Engineering University of California Santa Barbara United States Dept. of Electrical & Computer Engineering University of Texas at Austin Dept. of Electrical & Systems Engineering University of Pennsylvania Laboratory for Information & Decision Systems Massachusetts Institute of Technology

Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized. This framework faces several systems-oriented challenges which include (i) communication bottleneck since a large number of devices upload their local updates to a parameter server, and (ii) scalability as the federated network consists of millions of devices. Due to these systems challenges as well as issues related to statistical heterogeneity of data and privacy concerns, designing a provably efficient federated learning method is of significant importance yet it remains challenging. In this paper, we present FedPAQ, a communication-efficient Federated Learning method with Periodic Averaging and Quantization. FedPAQ relies on three key features: (1) periodic averaging where models are updated locally at devices and only periodically averaged at the server;(2) partial device participation where only a fraction of devices participate in each round of the training;and (3) quantized message-passing where the edge nodes quantize their updates before uploading to the parameter server. These features address the communications and scalability challenges in federated learning. We also show that FedPAQ achieves near-optimal theoretical guarantees for strongly convex and non-convex loss functions and empirically demonstrate the communication-computation tradeoff provided by our method. Copyright © 2019, The Authors. All rights reserved.

关键词： Scalability

Bayesian Neural networks Uncertainty Quantification with Cubature Rules

学校读者我要写书评

暂无评论

Bayesian Neural Networks Uncertainty Quantification with Cub...

International Joint Conference on Neural networks (IJCNN)

作者： Peng Wang Nidhal C. Bouaynaya Lyudmila Mihaylova Jikai Wang Qibin Zhang Renke He Automatic Control & Systems Engineering Dept. The University of Sheffield Information and Navigation College Air Force Engineering University The 32nd Research Institute of CETC Department of Automation University of Science and Technology of China Department of Electrical and Computer Engineering Rowan University

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Bayesian neural networks are powerful inference methods by accounting for randomness in the data and the network model. Uncertainty quantification at the output of neural networks is critical, especially for applications such as autonomous driving and hazardous weather forecasting. However, approaches for theoretical analysis of Bayesian neural networks remain limited. This paper makes a step forward towards mathematical quantification of uncertainty in neural network models and proposes a cubature-rule-based computationally-efficient uncertainty quantification approach that captures layer-wise uncertainties of Bayesian neural networks. The proposed approach approximates the first two moments of the posterior distribution of the parameters by propagating cubature points across the network nonlinearities. Simulation results show that the proposed approach can achieve more diverse layer-wise uncertainty quantification results of neural networks with a fast convergence rate.

关键词： Neural networks Uncertainty Bayes methods Computational modeling Gaussian distribution Two dimensional displays Weather forecasting

Heuristic Approach Towards Countermeasure Selection using Attack Graphs

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Stan, Orly Bitton, Ron Ezrets, Michal Dadon, Moran Elovici, Yuval Shabtai, Asaf Inokuchi, Masaki Ohta, Yoshinobu Yagyu, Tomohiko Dept. of Software and Information Systems Engineering Ben-Gurion University of Negev Security Research Laboratories NEC Corporation

Selecting the optimal set of countermeasures is a challenging task that involves various considerations and tradeoffs such as prioritizing the risks to mitigate and costs. The vast majority of studies for selecting a countermeasure deployment are based on a limited risk assessment procedure that utilizes the common vulnerability scoring system (CVSS). Such a risk assessment procedure does not necessarily consider the prerequisites and exploitability of a specific asset, cannot distinguish insider from outsider threat actor, and does not express the consequences of exploiting a vulnerability as well as the attacker's lateral movements. Other studies applied a more extensive risk assessment procedure that relies on manual work and repeated assessment. These solutions however, do not consider the network topology and do not specify the optimal position for deploying the countermeasures, and therefore are less practical. In this paper we suggest a heuristic search approach for selecting the optimal countermeasure deployment under a given budget limitation. The proposed method expresses the risk of the system using an extended attack graph modeling, which considers the prerequisites and consequences of exploiting a vulnerability, examines the attacker's potential lateral movements, and express the physical network topology as well as vulnerabilities in network protocols. In addition, unlike previous studies which utilizes attack graph for countermeasure planning, the proposed methods does not require re-generating the attack graph at each stage of the procedure, which is computationally heavy, and therefore it provides a more accurate and practical countermeasure deployment planning process. Copyright © 2019, The Authors. All rights reserved.

关键词： Risk assessment

Determining the coordinates of objects detected by a 1Tx + 4Rx antenna system using an artificial neural network;free space case

学校读者我要写书评

暂无评论

Determining the coordinates of objects detected by a 1Tx + 4...

International Workshop on Advanced Ground Penetrating Radar (IWAGPR)

作者： Vadym Plakhtii Gennadiy Pochanin Pierluigi Falorni Vadym Ruban Timothy Bechtel Luca Bossi School of Radio Physics Biomedical Electronics and Computer Systems V.N. Karazin Kharkiv National University Kharkiv Ukraine Department of Radiophysical Introscopy O.Ya.Usikov Institute for Radiophysics and Electronics of NAS of Ukraine Kharkiv Ukraine Department of Information Engineering Universit&#x00E0 degli Studi di Firenze Florence Italy Dept. of Earth &amp Environment Franklin &amp Marshall College Lancaster PA USA

ISBN: (数字)9781665422536

ISBN: (纸本)9781665446624

We investigated the implementation of artificial neural networks in the detection and discrimination of landmines and similar objects. The experimental data were obtained by using impulse GPR with a 1 Tx + 4Rx antenna system. The possibility of improving the input data by the moving average method was shown. Object identifications and positions are perfect for low noise and for object positions directly under the antenna array. Accuracy declines with increased noise and with distance from the antenna array. For positions of objects that are offset from the training data, the position is still determined with the greatest possible accuracy. The artificial neural network has proven successful in the task of determining the type and positions of the test objects.

关键词： Ground penetrating radar Landmine detection Training data Artificial neural networks Radar antennas Ultra wideband antennas Object recognition