Co-sponsors:

tl_files/sponser_pic/nict_new.png
tl_files/sponser_pic/uni.jpg

Technical co-sponsors:

tl_files/sponser_pic/Kmitl.jpg
tl_files/sponser_pic/XJTLU.jpg
tl_files/sponser_pic/naist.jpg
tl_files/sponser_pic/kisti.png
tl_files/sponser_pic/apnna.gif
tl_files/cfp/image019.png
tl_files/sponser_pic/logo_top_sx.gif

The 2018 International Workshop on Artificial Intelligence and Cybersecurity

Co-sponsorship: UNITEC, NICT 

Technical co-sponsorship: KMITL, XJTLU, NAIST, KISTI, APNNA, ENNS, INNS

 

You are cordially invited to submit papers to the 2018 International Workshop on Artificial Intelligence and Cybersecurity and participate in the 2018 Cybersecurity Data Mining Competition. The two events are associated with the 25th International Conference on Neural Information Processing (ICONIP 2018), Siem Reap, Cambodia, December 14−16, 2018. AICS 2018 workshop and CDMC 2018 award ceremony will be both co-held with ICONIP 2018.

Objective

The purpose of the 11th International Data Mining and Cybersecurity Workshop is to raise the awareness of cybersecurity, promote the potential of industrial applications, and give young researchers exposure to the main issues related to the topic and to ongoing works in this area. AICS 2018 will provide a forum for researchers, security experts, engineers, and students to present latest research, share ideas, and discuss future directions in the fields of data mining and cybersecurity.

Paper Submission & Publication

Authors are invited to submit papers on novel and mature work, of up to 12 pages in Springer LNCS format (with up to 2 additional pages for an extra charge). Please submit your papers via the ICONIP submission website, indicating the paper is devoted to AICS 2018 in the option list. All accepted papers will be published in the proceeding of ICONIP 2018, an LNCS publication with Springer.

Important dates

Paper Submission: June 1, 2018

Acceptance Notification: August 1, 2018

Camera-ready Submission: September 1, 2018

Workshop: December 14-16, 2018

Submission

Online Paper Submission

Instructions for Final Camera-Ready Paper Submission

Please follow the following six steps to prepare your camera-ready paper and submit the required materials in the above online submission system.

I. Revise your paper as soon as possible based on the comments in the reviews sent to you by email. You may also view the reviewers’ ratings, comments, and/or suggestions about the paper in your author’s account of the AICS 2018 Online Submission System. Please take the opportunity to improve the presentation of the paper.

II. Please prepare your paper in the EXACT FORMAT as the sample paper for Lecture Notes in Computer Science (LNCS) including reference format. Failure to do so may result in the exclusion of your paper from the proceedings. In the Information for LNCS Authors site, you are able to download the source files including LaTeX2e class file, sample file, word template.

NOTICE: Each paper is allowed to have 8 pages in the final camera-ready copy without paying extra charges. Each paper can have a MAXIMUM of 10 pages in the final camera-ready copy. If your paper is more than 8 pages in length in the final camera-ready copy without paying extra page charges (US$50/each extra page), we will not publish your paper, and we will not refund your registration payment. Each registration can have one more additional paper. Each additional paper is subject to extra charge. Details see the conference registration page.

III. Fill out the copyright form. A signed Copyright Form must be submitted for each paper. Please download the Copyright Form at Copyright Form for ICONIP 2018

NOTICE: Each paper is allowed to have up to 8 pages in the final camera-ready copy without paying extra charges. Each paper can have a MAXIMUM of 10 pages in the final camera-ready copy. If your paper is more than 8 pages in length in the final camera-ready copy without paying extra page charges (US$50/each extra page), we will not publish your paper, and we will not refund your registration payment. Each registration can have one more additional paper. Each additional paper is subject to extra charge. Details see the conference registration page.

IV. Submit the following files for your final submission via the above AICS 2018 Online Paper Submission System:
(1) Scanned signed copyright form.
(2) For LaTeX users, please submit:
i) LaTeX files for the text and PS/EPS or PDF/JPG files for all figures.
ii) Any further style files and fonts you have used together with your source files and that are not generally available at CTAN. iii) Final DVI file (for papers prepared using LaTeX/TeX)
iv) Final PDF file (for reference).
(2') For other users (other than LaTeX/TeX), please submit RTF files and a PDF file.

NOTICE: Please compress all necessary files into one file in the format of ZIP. We highly recommend you use your paper ID as the file name for the compressed file and pdf file. For example, if your paper ID is 35, you can save your files as 35.tex, 35.rar, 35.pdf.

V. If you have not chosen to present your paper(s) orally or by poster, please select one option when you submit your final version paper. If you have done this and decide to change your mind, you still are able to change the method of presentation.

VI. Register for AICS 2018 in the conference registration page. Publication of a paper in the proceedings requires that at least one author for the paper registers for the conference.

Title: Learning Adversarially for Robust Pattern Recognition

Prof. Kaizhu Huang

Head of Department, Electrical and Electroniccal Engineering, Xi’an Jiaotong-Liverpool University, China

Abstract

Learning adversarially is an active and interesting research direction in machine learning. In particular, adversarial examples, referred to as augmented data points generated by imperceptible perturbation of input samples, have recently drawn much attention. Being difficult to distinguish from real examples, such adversarial examples could change the prediction of many of the best machine learning models including the state-of-the-art deep learning models. Recent attempts have been made to build robust models that take into account adversarial examples. However, these methods can either lead to performance drops, or are ad-hoc in nature and lack mathematic motivations. In this talk, we propose a unified framework to build robust machine learning models against adversarial examples. More specifically, using the unified framework, we develop a family of gradient regularization methods that effectively penalize the gradient of loss function w.r.t. inputs. Importantly, such gradient regularization terms are shown highly robust to perturbations both theoretically and empirically. Our proposed framework is appealing in that it offers a unified view to deal with adversarial examples. It incorporates another recently-proposed famous perturbation based approach as a special case. In addition, we make both theoretical and empirical analysis on adversarial examples and present some visual effects that are not deemed to exist. By applying this technique to deep learning networks, we conduct a series of experiments and achieve robust and encouraging results in pattern recognition.​

Biography

tl_files/newwebfiels/KHuang.jpegKaizhu Huang is currently a Professor and Head, Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, China. He is also the founding director of Suzhou Municipal Key Laboratory of Cognitive Computation and Applied Technology. Prof. Huang has been working in machine learning, neural information processing, and pattern recognition. He was the recipient of 2011 Asia Pacific Neural Network Society (APNNS) Younger Researcher Award. He also received Best Book Award in National Three 100 Competition 2009. Until October 2018, he has published 8 books in Springer and over 140 international research papers (about 60 SCI-indexed international journals) e.g., in journals (JMLR, Neural Computation, IEEE T-PAMI, IEEE T-NNLS, IEEE T-BME, IEEE T-Cybernetics) and conferences (NIPS, IJCAI, SIGIR, UAI, CIKM, ICDM, ICML, ECML, CVPR). He serves as associated editors in three international journals and board member in three international book series. He has been sitting in the grant evaluation panels in Hong Kong RGC, Singapore AI programmes, and NSFC, China. He served as chairs in many international conferences and workshops such as ICONIP, AAAI, ACML, ICDAR, ACPR, SDA, and DMC.

 

 

Title: Rebellion of IoT: Infected Massive IoT Devices Observed through Darknet

Dr. Daisuke Inoue

Director, Cybersecurity Laboratory, National Institute of Information and Communications Technology, Japan

Abstract

During the last five years, targets of Cyberattack have been changing from PCs to IoT devices. Consequently, infected IoT deceives are massively and continuously increasing even now. In this talk, we present an actual situation of the infected IoT deceives observed through a large-scale darknet (unused IP addresses) monitoring and analysis system called NICTER. We also show some case studies of coordinated vulnerability disclosure of IoT devices (e.g., a mobile router and home routers) in Japan.

Biography

tl_files/newwebfiels/DInoue.jpgDaisuke Inoue received his B.E. and M.E. degrees in electrical and computer engineering and Ph.D. degree in engineering from Yokohama National University in 1998, 2000 and 2003, respectively. He joined Communications Research Laboratory (CRL), Japan, in 2003. CRL was relaunched as National Institute of Information and Communications Technology (NICT) in 2004, where he is currently the director of Cybersecurity Laboratory. He received several awards including the best paper award at the 2002 Symposium on Cryptography and Information Security (SCIS 2002), the commendation for science and technology by the minister of MEXT, Japan, in 2009, the Good Design Award 2013, the Asia-Pacific Information Security Leadership Achievements (ISLA) 2014, the award for contribution to Industry-Academia-Government Collaboration by the minister of MIC, Japan, in 2016, and the Maejima Hisoka Award, in 2018.

 

Please be noted that all participants to the AICS 2018 workshop are required to register at ICONIP 2018. For more information about registration, please see here

Program of the 11th International Workshop on Artificial Intelligence and Cyber Security

15 December 2018

Sokha Siem Reap Resort & Convention Center, Siem Reap, Cambodia

Date/Time

Topic and Speaker

  Session 1
11:30-12:10

Invited Talk: Learning Adversarially for Robust Pattern Recognition

Prof. Kaizhu Huang, Xi’an Jiaotong-Liverpool University, China

  Conference Lunch
13:30-14:10

Invited Talk: Rebellion of IoT: Infected Massive IoT Devices Observed through Darknet

Dr. Daisuke Inoue, National Institute of Information and Communications Technology (NICT), Japan

14:10

Winner Presentation of CDMC 2018 Competition

Xiang Zhao, Weixin Zeng, Peixin Huang, Wenzhe Hou, Ning Pang and Yang Fang

14:30

Mobile Malware Detection - an Analysis of the Impact of Feature Categories

Mahbub E Khoda, Joarder Kamruzzaman, Iqbal Gondal and Tasadduq Imam

14:50

Employ Decision Value for Binary Soft Classifier Evaluation with Crispy Reference

Lei Zhu, Tao Ban, Takeshi Takahashi and Daisuke Inoue

15:10

Deep Transfer Learning Via Minimum Enclosing Balls

Zhilong Deng, Fan Liu, Jiangjiang Zhao, Qiang Wei and Shaoning Pang

15:30-15:50

Coffee Break

  Session 2
15:50

Improving DNN Performance with Kernelized Min-Max Objective

Kai Yao, Kaizhu Huang, Rui Zhang and Amir Hussain

16:10

Handling Concept Drift in Time-series Data: Meta-cognitive Recurrent Recursive-Kernel OS-ELM

Zongying Liu, Chu Kiong Loo and Kitsuchart Pasupa

16:30

Graph Matching based on Fast Normalized Cut

Yang Jing, Yang Xu, Zhou Zhangbing and Liu Zhiyong

16:50

Overcoming Catastrophic Forgetting with Self-adaptive Identifiers

JFangzhou Xiong, Zhiyong Liu and Xu Yang

17:10

Task and Instance Quadratic Ordering for Active Online Multitask Learning

Jing Zhao, Shaoning Pang, Iman Tabatabaei Ardekani, Yuji Sekiya and Daisuke Miyamoto

The conference hotel will be the Sokha Siem Reap Resort & Convention Center. For more info, please see http://www.sokhahotels.com/siemreap/