Adversarial machine learning has recently received great attention in machine learning, especially deep learning. In particular, researchers have noted that certain augmented data points intentionally generated by imperceptible perturbation of samples can adversely impact the predictive capability of many of the best machine learning and data mining models, including state-of-the-art deep learning models. These imperceptible attacks are termed adversarial examples. Fig.1 shows an illustration of adversarial examples indicating the vulnerability of machine learning models. Exploitation of typically adversarial training, various attacking or defense based approaches have been developed. Assuring the robustness and security of machine learning algorithms in adversarial settings have become an important concern in the machine learning and computational intelligence research community.
Fig.1. Illustration of adversarial example. A panda image would be misclassified by state-of-the-art deep neural networks as a gibbon with a high confidence after adversarial noise is added (from Goodfellow 2014).This timely Workshop aims to provide professionals, researchers, and technologists with a shared interdisciplinary forum to exchange, discuss, and share state-of-the-art theories and applications of secure and adversarial machine learning, particularly in deep neural networks and data mining approaches.
Program ：TBD
Format:
Schedule: Tutorial + Invited speech+ Oral presentations.Duration: Half DayTargeted Audience:
Researchers, graduate students in computational intelligence and practitioners caring about the reliability and robustness of learning approaches.Topic of Interest
Topics of interest include, but not limited to, the following aspects:
- Foundations of understanding adversarial machine learning
- Property analysis for adversarial machine learning, particularly on adversarial examples
- Explainable adversarial learning
- Visualization of adversarial training
- Robust analysis of adversarial machine learning
- Generalization analysis of adversarial machine learning
- Connection of adversarial machine learning with regularization
- Distributional robust optimization theory for adversarial machine learning
- Theory and algorithms for attacking with adversarial learning
- Attacking on audio signals with adversarial learning
- Attacking on images and videos with adversarial learning
- Attacking on text with adversarial learning
- Attacking on structured data with adversarial learning
- Adversarial attacking based on gradient regularized methods
- Adversarial attacking based on distribution
- Adversarial attacking based on stochastic generation of adversarial examples
- Adversarial attacking with region based methods
- Adversarial attacking in manifold space
- Theory and algorithms of defending adversarial attacks
- Robust generative adversarial networks to adversarial attacks
- Robust supervised neural networks to adversarial attacks
- Robust semi-supervised deep learning to adversarial attacks
- Robust statistical learning models to adversarial attacks
- Robust data mining approaches to adversarial attacks
- Robust data approximation, dimensional reduction, clustering to adversarial attacks
- Other learning techniques with safe strategies
- Novel applications of adversarial learning and security
- Business data security with adversarial training
- Decision making with adversarial training
- Data augmentation with adversarial training
- Counterfactual reasoning with security
- Medical / health informatics with security
- Text mining with security
- Biological data analysis with security
- Graph data analysis with security
- Time-series prediction (financial predication) with security
- Biometric recognition with security
- Other related adversarial learning and mining methods with security
Submission and Key Dates:
- Paper Submission:
March 15 2020 March 31st 2020 (extended) - Paper Notification:
April 15 2020 April 30th 2020 (extended)
Papers are invited to submit through easychair :
AMLAS 2020. Any submission must comply with the guidelines of WCCI 2020. Detailed instructions can be seen here.
Submission instructionsPublication:
All the accepted papers will be invited to be published in the international journals: either Springer Big Data Analytics or a special issue of Cognitive Computation (ISI impact factor 4.287) subject to further extension.
Organizers:
Kaizhu Huang, Professor, Xi’an Jiaotong-Liverpool University,
Kaizhu.Huang@xjtlu.edu.cnBio: Kaizhu 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. He has published 8 books in Springer and over 170 international research papers including 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 programs, and NSFC, China. He served as chairs in many international conferences and workshops such as ICONIP, AAAI, ACML, ICDAR, ACPR, SDA, and DMC. His personal website can be seen in
http://www.premilab.com/KaizhuHUANG.ashx.
Ping Guo, Professor, Beijing Normal University,
pguo@bnu.edu.cnBio: IEEE senior member, CCF senior member, Chair of IEEE CIS Beijing Chapter (2015-2016). His research interests include computational intelligence theory and its applications in pattern recognition, image processing, software reliability engineering, and astronomical data processing. He hold 6 patents and has published more than 300 papers, and two books: “Computational intelligence in software reliability engineering”, and “Image semantic analysis.” He received 2012 Beijing municipal government award of science and technology (third rank) entitled "regularization method and its application". Professor Guo received his master's degree in optics from the Department of physics, Peking University, and received his Ph.D degree from the Department of computer science and engineering, Chinese University Hong Kong. His personal home page can be seen in
http://sss.bnu.edu.cn/~pguo.
Zenglin Xu, Professor, University of Electronic Science and Technology of China,
zlxu@uestc.edu.cnBio: Zenglin Xu is a Professor in School of Computer Science and Engineering at University of Electronic Science and Technology of China(UESTC). He obtained his PhD in Computer Science and Engineering from the Chinese University of Hong Kong, and after that he worked at Max-Planck Institute for Informatics, Germany and Purdue University, USA. He is the founding director of the Statistical Machine Intelligence and LEarning (SMILE) Lab. His research interests include machine learning and its applications on social network analysis, health informatics, and cyber security analytics. He has published over 70 papers in prestigious journals and conferences such as NIPS, ICML, IJCAI, AAAI, IEEE PAMI, IEEE TNN, etc. He is a recipient of China Thousand Talents(Youth) Program. He is also the recipient of the APNNS young researcher award in 2016, and the best student paper honorable mention of AAAI 2015 and ACML 2016. Dr. Xu has been a PC member or reviewer to a number of top conferences such as NIPS, ICML, AAAI, IJCAI, etc. He currently serves as an associated editor to Neural Networks and Neurocomputing. His personal home page can be seen in
http://smilelab.uestc.edu.cn/.
Amir Hussain, Professor, Edinburgh Napier University.
A.Hussain@napier.ac.ukBio: Amir Hussain is a professor and a founding Director of the Cognitive Big Data and Cybersecurity(CogBiD) Research in Edinburgh Napier University (UK), managing over 25 academic and research staff. Professor Hussain’s research interests are cross-disciplinary and industry focused, aimed at pioneering brain-inspired, cognitive Big Data technology for solving complex real-world problems. In 2017-18, he was ranked, in an independent survey (published in Elsevier’s Information Processing and Management Journal), as one of world’s top two most productive, highly-cited researchers in (Big Data) sentiment analytics (since 2000). He has (co)authored three international patents, more than 400 publications, with approximately 150 journal papers. He is founding Editor-in-Chief of (Springer Nature’s) Cognitive Computation journal (SCI Impact Factor (IF): 3.48) and BMC Big Data Analytics journal (published by BioMed Central (BMC)-part of Springer Nature). He has been appointed Associate Editor of several other world-leading journals including, IEEE Transactions on Neural Networks and Learning Systems (SCI IF 6.1), Elsevier’s Information Fusion journal (SCI IF: 5.9), the IEEE Transactions on Emerging Topics in Computational Intelligence, and the IEEE Computational Intelligence Magazine (SCI IF: 6.34).
Past Records in Organizing Workshops
- International Workshop on Understanding and Harnessing Adversarial Examples in Data Mining, ICDM 2019
- International Workshop on Artificial Intelligence for Business Security, IJCAI 2019
- Adversarial Examples for Robust Learning Systems: Concepts, Theory, and Applications, IEEE SMC 2019
- International Workshop on Data Mining and Cybersecurity, ICONIP 2013-2018
- 5th International Workshop on Scalable Data Analytics, WSDM 2015
Remarks:The above workshops were very popularly held and attracted a large number of attendees. The intended workshop is a significantly further expansion of the above activities, presenting a more comprehensive and more thorough workshop with the audience targeted as the researchers in computational intelligence.
Main Contact
Kaizhu Huang, Professor, Xi’an Jiaotong-Liverpool University
Email: Kaizhu.Huang@xjtlu.edu.cn
Mail Address: EE510A, Engineering Building, Xi’an Jiaotong-Liverpool University
Ren’ai Road, No. 111, SIP, Suzhou, 215123, Jiangsu Province, China