EditorialAI-Driven Cyber Security Analytics and Privacy Protection

Jiageng Chen ,1 Chunhua Su,2 and Zheng Yan 3

1Central China Normal University, China2University of Aizu, Japan3Xidian University, China

Correspondence should be addressed to Jiageng Chen; chinkako@gmail.com

Received 5 November 2019; Accepted 5 November 2019; Published 30 November 2019

Copyright © 2019 Jiageng Chen et al. �is is an open access article distributed under the Creative Commons Attribution License,which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

�e cyber security protection has gone through a rapid de-velopment in today’s internet connected world.With the wideapplication of the booming technologies such as the Internetof �ings (IoT) and the cloud computing, huge amount ofdata are generated and collected. While the data can be usedto better serve the corresponding business needs, they alsopose big challenges for the cyber security and privacy pro-tection. It becomes very di�cult if not impossible to discoverthe malicious behavior among the big data in real time. �us,this gives rise to the cyber security solutions which are drivenby AI-based technologies, such as machine learning, statisticalinference, big data analysis, deep learning, and so on. AI-driven cyber security analytics has already found its appli-cations in the next generation �rewall which includes theautomatic intrusion detection system, encrypted tra�cclassi�cation, malicious software detection, and so on. In thearea of cryptography, AI-driven solution starts to help theresearchers optimize the algorithm design and can largelyreduce the cryptanalysis e�ort such as searching the di�er-ential trails which is crucial in di�erential cryptanalysis.Recently, the idea of generative adversary network was ap-plied to building the automatic encryption algorithm, whichmakes a �rst move towards making an intelligent protectionsolution without the interference of the human e�ort. On thecontrary, individual’s privacy is under threat given the AI-based systems.�e rise of AI-enabled cyberattacks is expectedto cause an explosion of network penetrations, personal datathefts, and an epidemic-level spread of intelligent computerviruses. �us, another future trend is to defend AI-drivenattacks by using AI-driven techniques, which will possiblylead to an AI arms race. AI-driven security solution is one ofthe fastest growing �elds which bring together researchers

from multiple areas such as machine learning, statistics, bigdata analytics, and cryptography to �ght against the advancedcyber security threats. �e purpose of this special issue is topresent the cutting-edge research progress from both aca-demia and industry, with a particular emphasis on the newtools, techniques, concepts, and applications concerning theAI-driven cyber security analytics and privacy protection. Abrief summary of all the accepted papers is provided asfollows.

In the paper by Y. Zhao et al., a novel feature extractionmethod of hybrid gram (H-gram) with cross entropy ofcontinuous overlapping subsequences was proposed basedon the dynamic feature analysis of malware, which imple-mented semantic segmentation of a sequence of API calls orinstructions. �e experimental results showed that theH-grammethod can distinguish the malicious behaviors andis more e�ective than the �xed-length n-gram in all fourperformance indexes of the classi�cation algorithms such asID3, Random Forest, AdboostM1, and Bagging.

�e paper by T. Hu et al. proposed a user authenticationmethod based on mouse biobehavioral characteristics anddeep learning, which can accurately and e�ciently performcontinuous identity authentication on current computerusers to address insider threats. An open source dataset withten users was applied to carry out experiments, and theexperimental results demonstrated the e�ectiveness of theapproach. �e proposed approach can complete a userauthentication task approximately every 7 seconds, with afalse acceptance rate of 2.94% and a false rejection rate of2.28%.

In the paper by G. Huang et al., the algorithm MFS_AN(mining fault severity of all nodes) was proposed to mine the

HindawiSecurity and Communication NetworksVolume 2019, Article ID 1859143, 2 pageshttps://doi.org/10.1155/2019/1859143

key nodes from the software network. A weighted softwarenetwork model was built by using functions as nodes, withrelationships as edges, and times as weight. By exploiting therecursive method, a fault probability metric FP of a functionis defined according to the fault accumulation characteristic,and a fault propagation capability metric FPC of a function isproposed according to the fault propagation characteristic.Based on the FP and FPC, the fault severity metric FS was putforward to obtain the function nodes with larger fault se-verity in the software network. Experimental results on tworeal software networks showed that the algorithm MFS_ANcan discover the key function nodes correctly and effectively.

#e paper by H. Park proposed the Secure InformationSharing System (SISS) model with the main method as agroup key cryptosystem. SISS figured out important prob-lems of group key systems. (1) #e newly developed equa-tions for encryption and decryption can eliminate the re-keying and redistribution process for every membershipchange of the group, keeping the security requirements. (2)#e new 3D stereoscopic image mobile security technologywith AR (Augmented Reality) solved the problem of con-spiracy by group members. (3) SISS used the reversed one-way hash chain to guarantee Forward Secrecy and BackwardAccessibility (security requirements for information sharingin a group). It showed that the security analysis of SISSaccording to the Group Information-sharing Secrecy andexperiment on the performance of SISS. As a result, SISSmade it possible to securely share sensitive information fromcollaborative works.

#e paper by Y. Zhao et al. addressed the problem ofCCA secure public key encryption against after-the-factleakage without NIZK proofs. To obtain security againstchosen ciphertext attack (CCA) for PKE schemes againstafter-the-fact leakage attack (AFL), previous works followedthe paradigm of “double encryption” which needs non-interactive zero knowledge (NIZK) proofs in the encryptionalgorithm. #is paper presented an alternative way toachieve AFL-CCA security via lossy trapdoor functions(LTFs) without NIZK proofs. Formalization of definition ofLTFs secure against AFL (AFLR-LTFs) and all-but-onevariants (ABO) was given. #en, it showed how to realizethis primitive in the split-state model. #is primitive can beused to construct an AFLR-CCA-secure PKE scheme in thesame way as the method of “CCA from LTFs” in traditionalsense.

In the paper by J. Ren et al., a software buffer overflowvulnerability prediction method by using software metricsand a decision tree algorithm was proposed. First, thesoftware metrics were extracted from the software sourcecode, and data from the dynamic data stream at the func-tional level were extracted by a data mining method. Second,a model based on a decision tree algorithm was constructedto measure multiple types of buffer overflow vulnerabilitiesat the functional level. Finally, the experimental resultsshowed that the method ran in less time than SVM, Bayes,adaboost, and random forest algorithms and achieved82.53% and 87.51% accuracy in two different data sets.

In the paper by S. Zhao et al., a three-layer classifier usingmachine learning to identify mobile traffic in open-world

settings was proposed. #e proposed method had the ca-pability of identifying the traffic generated by unconcernedapps and zero-day apps; thus, it can be applied in the realworld. A self-collected dataset that contains 160 apps wasused to validate the proposed method. #e experimentalresults showed that the classifier achieved over 98% pre-cision and produced a much smaller number of false pos-itives than that of the state-of-the-art.

Conflicts of Interest

#e guest editors declare that there are no conflicts of in-terest regarding the publication of the special issue.

Acknowledgments

We would like to express our gratitude to all authors whomade this special issue possible. We hope this collection ofarticles will be useful to the scientific community.#e launchof this special issue was supported in part by the NationalNatural Science Foundation of China under Grant no.61702212 and the Fundamental Research Funds for theCentral Universities under Grand no. CCNU19TS017.

Jiageng ChenChunhua SuZheng Yan

2 Security and Communication Networks

International Journal of

AerospaceEngineeringHindawiwww.hindawi.com Volume 2018

RoboticsJournal of

Hindawiwww.hindawi.com Volume 2018

Hindawiwww.hindawi.com Volume 2018

Active and Passive Electronic Components

VLSI Design

Hindawiwww.hindawi.com Volume 2018

Hindawiwww.hindawi.com Volume 2018

Shock and Vibration

Hindawiwww.hindawi.com Volume 2018

Civil EngineeringAdvances in

Acoustics and VibrationAdvances in

Hindawiwww.hindawi.com Volume 2018

Hindawiwww.hindawi.com Volume 2018

Electrical and Computer Engineering

Journal of

Advances inOptoElectronics

Hindawiwww.hindawi.com

Volume 2018

Hindawi Publishing Corporation http://www.hindawi.com Volume 2013Hindawiwww.hindawi.com

The Scientific World Journal

Volume 2018

Control Scienceand Engineering

Journal of

Hindawiwww.hindawi.com Volume 2018

Hindawiwww.hindawi.com

Journal ofEngineeringVolume 2018

SensorsJournal of

Hindawiwww.hindawi.com Volume 2018

International Journal of

RotatingMachinery

Hindawiwww.hindawi.com Volume 2018

Modelling &Simulationin EngineeringHindawiwww.hindawi.com Volume 2018

Hindawiwww.hindawi.com Volume 2018

Chemical EngineeringInternational Journal of Antennas and

Propagation

International Journal of

Hindawiwww.hindawi.com Volume 2018

Hindawiwww.hindawi.com Volume 2018

Navigation and Observation

International Journal of

Hindawi

www.hindawi.com Volume 2018

Advances in

Multimedia

Submit your manuscripts atwww.hindawi.com