Journal of Information Security Reserach

From “Latter-wit” to “Nip in the Bud”

2017, 3(11): 962-965.

Asbtract ( )

PDF (700KB) ( )

Related Articles | Metrics

A Survey of the Basic Technology and Application of Block Chain

2017, 3(11): 968-980.

Asbtract ( )

PDF (11096KB) ( )

References | Related Articles | Metrics

At 7:00 pm on September 14th 2017, Bitcoin China issued a notice that digital asset trading platform will stop all trading business on September 3. The well known Bitcoin collapse completely. However, as the beginning of building a value-transferring network for human, the blockchain technology behind Bitcoin is still worthy of paying more attention and in-depth research. The blockchain is an integrates application with distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and so on. This technology has been widely concerned by the government, enterprises and scholars. At present, the application of block chain has been extended to the Internet of Things, supply chain management and other fields. In this paper, we first give the definition and the classification of the block chain. Then, the features of the block chain and the workflow of the system are analyzed. Nest, the system framework and the core technology are introduced. Finally, the typical application of blockchain are discussed in the idea of the zone pain and the block chain solution in financial and non -financial areas.

A Glimpse at Blockchain: From the Perspective of Privacy

2017, 3(11): 981-989.

Asbtract ( )

PDF (7718KB) ( )

References | Related Articles | Metrics

Blockchain, as an open decentralized ledger technology among a P2P network, is the supporting technology for cryptocurrencies such as Bitcoin and etc. Blockchain enables low-cost trust among counterparts and is considered promising in cross-border payment, credentials, supply chain and etc., attracting wide attention from financial and government institutions. However, while the blockchain guarantees trust via transparency, privacy issue occurs. When all the transactions are exposed to the public and maliciously explored, user privacy will be heavily threatened. Recently, various work have been done to address the privacy issue, leading to the necessity of a survey paper. In this paper, we will first figure out the privacy leakage by examples. Then, comprehensive introduction and analysis of the state-of-the-art solutions, such as Dash, Monero, Zcash, Hawk, Quorum and Coco Framework will be present. Last, we will summarize the technologies and give an outlook.

Network intrusion detection model based on convolutional neural network

2017, 3(11): 990-994.

Asbtract ( )

PDF (3567KB) ( )

References | Related Articles | Metrics

Network intrusion detection is an important component of network security. At present, the popular detection technology is to use the traditional machine learning algorithm to train the intrusion samples, so as to obtain the intrusion detection model. However, these algorithms have the disadvantage of low detection rate. Depth learning is an algorithm that automatically extracts features from samples. In view of the fact that the accuracy of intrusion detection is not high in traditional machine learning technology, this paper proposes a network intrusion detection model based on convolutional neural network algorithm. The model can automatically extract the effective features of intrusion samples, so that the intrusion samples can be accurately classified. Experimental results on KDD99 datasets show that the proposed model can greatly improve the accuracy of intrusion detection.

Study on Metal Attributions of Defense Decision of Networks Security from Cognitive Views

2017, 3(11): 995-999.

Asbtract ( )

PDF (4309KB) ( )

References | Related Articles | Metrics

The automatics decision capability is one of the key points to enhance the decision capability of the networks security decision system under the complex, dynamic and uncertain networks threat environment. In this paper , the mental factors of the automatics decision are classified from belief, motivation, plan and obligation etc. Based on the requirements of networks security defense first, and then, the belief, goal, tactical intention and obligation etc. automatics decision mental attributions are presented. And the modeling key points of the automatics mental attributions are analyzed. Finally, some mental attributions are modeled by AML (Agent Modeling Language).

Risk Control System For Mobile Bank Based on Artificial Intelligence

2017, 3(11): 1000-1005.

Asbtract ( )

PDF (4953KB) ( )

References | Related Articles | Metrics

With the popularity of smartphones and mobile Internet, more and more institutions, organizations and individuals have needs that through intelligent terminal and mobile Internet to deal with financial business. However, because of the complexity of the mobile Internet transactions and security issues intelligent terminal itself, trading information security have been increasingly serious threat, and may produce unpredictable economic losses. This article describes the mobile financial transactions as a whole, the proposed transaction scenario as the core to assist on the technology of artificial intelligence and big data to establish a hierarchical risk index evaluation system, and its application to Gui Yang Mobile Bank applied in the system.

The analysis of the application of biometric technology in commercial Banks

2017, 3(11): 1006-1010.

Asbtract ( )

PDF (4073KB) ( )

References | Related Articles | Metrics

Biological recognition technology as one of the main safety certification methods, in recent years becoming a hotspot in security technology of financial option. This paper summarizes the current application in the commercial bank including main types, methods and application scenes, analysis the main restricting factors in the financial industry development in standardized regulation, customer acceptability and the security of the biometric system itself, and further analysis that the commercial banks need to focus on data retained, system security and performance optimization of system framework and the development trend of biological recognition technology application in commercial banks.

Artificial Intelligence to Promote Precision Marketing Network

2017, 3(11): 1011-1016.

Asbtract ( )

PDF (4444KB) ( )

References | Related Articles | Metrics

With the rapid development of the Internet economy, China has fully entered the Internet era. Many Internet enterprises and traditional enterprises have some shortcomings in terms of the number of new users. Through the identification of users based on artificial intelligence technology based on identity information based on real consumer data analysis based on the results of the formation of personal portrait, the credit rating system can be consumer spending patterns, behavioral habits, credit conditions, such as target refinement Analysis, and ultimately achieve precision marketing, accurate diversion, to solve the traditional offline business and Internet business development of new users short board.

Study on loan fraud prevention algorithm based on maximum clique

2017, 3(11): 1017-1019.

Asbtract ( )

PDF (1505KB) ( )

References | Related Articles | Metrics

Financial institutions such as banks need to verify the authenticity of users when verifying their loan needs。 And a common method to confirm the user's identity is investigating several users' personal information by telephone。 Impostors can obtain user information through illegal channels because of increasing information security issues and impersonate real users to defraud the loan。 Everyone's speaker features are unique and unforgeable， so it’s feasible using voice data to authenticate。 Therefore， we introduce a loan fraud algorithm in this article。 We use users' telephone recordings to extract their voiceprint and build a speaker model library。 And so we found that users collections with similar voiceprint in order to identify fraud behavior。 At the end we comparing performance of GMM-UBM and I-vector based loan fraud algorithm。

Improved random forest algorithm and its application in Android malware detection

2017, 3(11): 1020-1027.

Asbtract ( )

PDF (4155KB) ( )

References | Related Articles | Metrics

In order to improve the efficiency of android malware detection, an improved random forest algorithm is proposed. It optimizes the subset of features selected in the process of splitting each node during the random forest generation process, and the model will be optimized by Cross Validation method. The experiment results show that improved random forest is superior to the original one in the problem of classifying android applications into normal, SMS Trojan, spyware, botnet with a higher precision(94.0%) and recall(90.5%). It can effectively detect different android malware, and the information and property of the users are guaranteed.

Research on Deceptive Technology of Mobile Browser Based on Fuzzing

2017, 3(11): 1028-1033.

Asbtract ( )

PDF (5267KB) ( )

References | Related Articles | Metrics

In view of the poor effectiveness of the current Android browser communication protocol security test scheme, this paper proposes a vulnerability mining method based on Fuzzy Test Technology in generation mode. The scheme adopts the data block correlation model to describe the protocol under test, then according to the structure of the protocol automation test script generation deformity data corresponding to the package as a test case, and the generated test cases were sent to the abnormal test target, and monitor customer mobile phone browser is abnormal and record the abnormal information, analysis how to lead to abnormal error. Experimental results show that the proposed scheme can more fully exploit the mobile browser vulnerability caused by protocol analysis and fuzzy test, and has the certain reliability.

Efficient and flexible attribute based encryption scheme in cloud computing

2017, 3(11): 1034-1039.

Asbtract ( )

PDF (4577KB) ( )

References | Related Articles | Metrics

Aiming at the security and privacy of data in the process of data sharing under cloud computing, An attribute-based encryption scheme with high efficiency and flexibility under cloud computing is proposed. The scheme encrypts the cloud storage data using the ciphertext policy attribute base algorithm, and the trusted third party adds the global identity to the user attribute set and aggregates the attribute public key associated with the ciphertext policy with the fixed-length ciphertext strategy so that the The ciphertext length is constant. The scheme effectively prevents the security risks caused by the conspiracy attack on the user data, selects the appropriate encryption algorithm and efficient public key encryption processing way to ensure the privacy of the dynamic data in the data sharing process, and achieves the data security at the lower cost Shared goals.

Research of Identity-Based Cryptography Application in Internet of Things

2017, 3(11): 1040-1044.

Asbtract ( )

PDF (4015KB) ( )

References | Related Articles | Metrics

With the widespread use of public key cryptography(PKI), there are some defects in the management also exposed, such as certificate of search, cancellation, storage, issuance and verify that all need to take up a lot of valuable network resources, and can lead to a larger storage overhead and computation overhead. Identity-based cryptography( IBC) is developed based on PKI, besides has the PKI technology advantages, mainly solved in the specific application of PKI security needs a large number of exchange of digital certificates, make security applications more easy to deploy and use. The IBC password technology USES asymmetric cryptography to encrypt and decrypt two sets of keys. Compared with the public key cryptosystem based on digital certificate, identity-based cryptosystem has don't need certificate center, has a higher safety performance, shorter key lengths and convenient key management, can be combined with Internet of things(iot) device identifier, solve identification in iot, key security issues such as link encryption, data protection.

On Secure Design of Automatic Fare Collection (AFC) System for City Rail

2017, 3(11): 1045-1052.

Asbtract ( )

PDF (6420KB) ( )

References | Related Articles | Metrics

With the city rail networks become more and more complex and intelligent, its automatic fare collection (AFC) system also becomes more and more complicated. Hence security protection mechanism for the AFC becomes necessary. An AFC system for city rail systems is designed in this paper. By using the cryptographic techniques, the designed AFC system is shown to be secure against impersonation attack, forgery attack, and cloning attack. The designed AFC system is also shown to have good extensibility, because the computational complexity in verifying the validity of the tickets and their balances does not depend on the number of the whole tickets.

Three “Sharp Weapons” of AI for Strengthening Financial Information Security

2017, 3(11): 1053-1056.

Asbtract ( )

PDF (736KB) ( )

Table of Content