The 2021 International Workshop on Artificial Intelligence and Cybersecurity

Co-organizer: NICT Co-sponsor: Federation University

Technical co-sponsorship: ICSDS, INNS and APNNA

You are cordially invited to submit papers to the 2021 International Workshop on Artificial Intelligence and Cyber Security (AICS2021) and participate the CDMC2021 data mining competition. The two events both in association to the 28th International Conference on Neural Information Processing (ICONIP2021), Bali, Indonesia.

Objective

The purpose of the 14th International Artificial Intelligence and Cyber Security Workshop (AICS2021) 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. AICS2021 will provide a forum for researchers, security experts, engineers, and research students to demonstrate new technologies, present latest research works, share ideas, and discuss future directions in the fields of artificial intelligence 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 AICS2021 in the option list. All accepted papers will be published in the Springer series of Lecture Notes in Computer Science (LNCS) and Communications in Computer and Information Science (CCIS).

Important dates

Paper Submission: 30th of June 2021

Acceptance Notification: 31st of August 2021

Camera-ready Submission: 30th of September 2021

Workshop Date: 8th December 2021

Title: Building Security and Privacy Assured Deep Neural Networks

Dr. Surya Nepal

CSIRO Data61, Australia

Abstract

AI/ML technology has the potential to bring significant benefits to the economy and society. It is a tremendous promise. The technology has been developed, deployed, and adopted in many real-life critical applications to fulfil its promise. It helps us to drive cars, doctors to make a diagnosis, employers to hire people, governments to create policies, make our cyberspace secure and safe, address the skill shortage through automation. However, it also introduces significant risks that need to be managed. For example, Backdoor attacks insert hidden associations or triggers to the deep learning models to override correct inference such as classification and make the system perform maliciously according to the attacker-chosen target while generally behaving in the absence of the trigger. In addition, it has been demonstrated that ML models learn more than necessary from the data and endanger individual’s privacy. Hence, AI/ML systems must have the properties of trustworthy computing, such as security and privacy. This talk first provides a brief overview of security and privacy issues in deep neural networks, then presents recent efforts in building trustworthy deep neural networks, and finally some challenges and opportunities.

Biography

tl_files/newwebfiels/snepal.jpgDr Surya Nepal is a Senior Principal Research Scientist at CSIRO Data61. He currently leads the distributed systems security group comprising 30+ research staff and 50+ postgraduate students. His main research focus is on the development and implementation of technologies in the area of cybersecurity and privacy and AI and Cybersecurity. He has more than 250 peer-reviewed publications to his credit. He is a member of the editorial boards of IEEE Transactions on Service Computing, ACM Transactions on Internet Technology, IEEE Transactions on Dependable and Secure Computing, and Frontiers of Big Data- Security Privacy and Trust. He is also currently holding the position of deputy research director at Cybersecurity Cooperative Research Centre (CRC).

Title: Fighting IoT Cyberattacks: Device Discovery, Attack Observation, and Security Notification

tl_files/newwebfiels/kyoshioka.jpgProf. Katsunari Yoshioka

National Yokohama University, Japan

Abstract

IoT cyber security has become one of the most important and challenging topics in recent years. In this talk, new trends in IoT cyber attacks, malware evolution, and efforts to discover and mitigate insecure and/or compromised devices are explained.

Title: Decentralized Learning for Anomaly Detection: Challenges and Opportunities

Dr. Tianwei Zhang

NTU, Singapore

Abstract

The rapid development of edge computing and deep learning technologies leads to the area of Artificial Intelligence of Things. Meanwhile, modern edge systems are also facing a variety of security threats when interacting with the complex and dynamic environment. Hence, it has become a popularity to train and deploy deep learning models on edge devices to perform anomaly detection and protect their runtime execution. The gap between large-scale deep learning models and resource-constrained devices call for the decentralized learning solution, where multiple participants train the target model collaboratively with high efficiency, generalization and privacy guarantee. In this talk, I will first present a case study about the anomaly detection with decentralized learning in the context of autonomous driving systems. Then, I will discuss some inherent privacy vulnerabilities in distributed learning, and innovative defense solutions to make the artificial intelligent systems more trustworthy and efficient.

Biography

tl_files/newwebfiels/tzhang.jpgDr. Tianwei Zhang is currently an assistant professor of School of Computer Science and Engineering, at Nanyang Technological University. He received his Bachelor’s degree at Peking University, China, in 2011, and the Ph.D degree in Electrical Engineering at Princeton University in 2017. His research focuses on computer system security. He is particularly interested in distributed system security, computer architecture security, and machine learning security. He has published more than 40 papers in top-tier AI, security and system conferences and journals.

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 2021 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 2021

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 2021 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 2021 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.

Please be noted that all AICS2021 participants are required to register at ICONIP2021.

A tentative program is available to download.

AICS2021 will be co-located with ICONIP2021, please find the Venue information via https://www.apnns.org/ICONIP2021/

Co-organizer:

tl_files/sponser_pic/nict_new.png

Co-sponsor:

tl_files/sponser_pic/FED_colour_logo.svg

Technical co-sponsors:

tl_files/sponser_pic/icsds.png
tl_files/sponser_pic/apnna.gif
tl_files/sponser_pic/logo_top_sx.gif