Introduction

Maintaining business security is essential for successful businesses and has become one of the biggest challenges in the business development. Typical business security issues include: content-based security, anomalous behavior detection, security in social networks and online ecommerce etc. In recent years, there have seen a dramatic increase in applications of artificial intelligence and data mining techniques to solve business security problems. However, this creates some new security challenges. The new artificial intelligent system itself may become a vulnerable and lucrative target to attackers. The AIBS 2019 workshop aims at providing a venue for presenting and discussing new developments to make the business more secure using AI techniques even when adversary adapts.

The workshop will bring together researchers from both computer security and machine learning communities. Our agenda will include contributed papers as well as invited talks from distinguished researchers in these joint areas. Moreover, the top-3 winner’s solutions from each track of the IJCAI-2019 Alibaba Adversarial AI Challenge (AAAC 2019) will also be presented. In addition, sufficient discussion time will be added to encourage linkages between researches in different sub-communities in order to establish new connections and long-term collaborations. We hope that this workshop will help identify new fundamental directions for future research and open a new way towards achieving a more secure business environment.

Program

ç

                Date: August 10th, 2019
                Venue: Naples 2606, Venetian Macao Hotel Resort, Macao, China.

Program

Accepted Papers

  • Sarah Cooney, Kai Wang, Elizabeth Bondi, Thanh Nguyen, Phebe Vayanos, Hailey Winetrobe, Edward Cranford, Cleotilde Gonzalez, Christian Lebiere and Milind Tambe. Signaling Just Enough: Learning to Find the Goldilocks Zone to Improve Adversary Compliance in Security Games
  • Wei He, Yue Xu and Liang Shi. Webshell Detection via Attention-Based Opcode Sequence Classification
  • Xin Zhang, Ning Jia and Ioannis Ivrissimtzis. Watermark retrieval from 3D printed objects via synthetic data training
  • Xiaoyu Tang and Jie Chen. Insider Threat: Data Exfiltration Detection using Node2Vec in Instance Message
  • Da Sun Handason Tam, Wing Cheong Lau, Bin Hu, Qiu Fang Ying, Dah Ming Chiu and Hong Liu. Identifying Illicit Accounts in Large Scale E-payment Networks - A Graph Representation Learning Approach
  • Xiaofeng Mao, Yuefeng Chen, Yuhong Li, Yuan He and Hui Xue. GAP++: Learning to generate target-conditioned adversarial examples
  • Zheng Zhao, Xiaoyang Wang and Zhengmao Gong. AAAC2019 : Generating Transferable Adversarial Examples
  • Xiaoyang Wang, Zhengmao Gong and Zheng Zhao. AAAC2019 : Decreasing Adversarial Perturbations Through Mapping Function Transforms
  • Qiao Yang, Yingyuan Jiang and Junpeng Wang. Composition of Multiple Image Domain Transformations to Defend Against Adversarial Attacks
  • Bin Chen, Yongle Liu, Yujie Sun and Jianhua Su. Attention-ATN: A Method to Generate Transferable Adversarial Examples
  • Qiao Yang, Yingyuan Jiang and Junpeng Wang. Adversarial Training Method via feature maps guidance
  • Xiaoxiong Ma, Renzhi Wang and Cong Tian. Enhancing Transferability of Adversarial Examples by Using multiple Cross-Entropy Losses
  • Mrinal Rawat and Chandrasekhar Anantaram. Contextual Masking of Sensitive Information in Machine Transcribed Speech
  • Nishtha Agrawal and Durga Toshniwal. PFSR: Parallelized FP-Tree based Sensitive Pattern Removal Approach
  • Khushbu Jhunjhunuwala and Durga Toshniwal. Spam Detection Using Semantic and Temporal Analysis in Reviews
  • Shalini Jangra and Durga Toshniwal. A PSO Inspired Algorithm to Improve Privacy of Business Sensitive Patterns
  • Jinyin Chen, Ruoxi Chen, Haibin Zheng, Hui Xiong and Shouling Ji. RAD-PAW: Reconstructed Adversarial Defense via Pixel Attention Weight
  • Zhendong Zhang, Cheolkon Jung and Xiaolong Liang. Adversarial Defense by Suppressing High-frequency Components
  • Shufei Zhang, Kaizhu Huang, Rui Zhang and Amir Hussain. Adversarial Training with Second Order Information
  • Jia Song, Qing Zhang and Henliang Luo. Attack Defense and Bot Detection System Design for Text-based Slide CAPTCHA
  • Yu Pang. Multi-strategy Integration Architecture for Pornographic Web Site Detection
  • Xiao Xu, Yijun Chen, Xingyi Yang, Yining Hu, Lizhe Xie and Zheng Wang. Information Redundancy Minimization for Adversarial Defense
  • Fanyou Wu, Bedrich Benes, Rado Gazo and Eva Haviarova. Efficient Project Gradient Descent for Ensemble Adversarial Attack

Honor Chairs

Xiansheng Hua, Alibaba DAMO Academy, IEEE Fellow
Kui Ren, Distinguished Professor of Zhejiang University, IEEE Fellow, ACM Distinguished Scicentist
Zhiguo Gong, University of Macau

Organizers

Quan Lu

Quan Lu

Principal Engineer, Alibaba Group
Email: luquan.lq@alibaba-inc.com

Quan Lu is a principal engineer in Alibaba group. He holds a Ph.D. from the University of Southern California and currently leads the data & algorithm team in Alibaba’s Security Department. Dr. Lu has over 15 years of experience in applying large-scale machine learning and data mining methods into solving real-world industrial problems in areas such as cybersecurity, risk management and online advertising. Prior to joining Alibaba, Dr. Lu had led the research team as a Senior Director at Yahoo! display ads. He has published more than 20 papers at top international conferences and holds a number of US patents.

Shouling Ji is a ZJU 100-Young Professor in the College of Computer Science and Technology at Zhejiang University and a Research Faculty in the School of Electrical and Computer Engineering at Georgia Institute of Technology (Georgia Tech). He received a Ph.D. degree in Electrical and Computer Engineering from Georgia Institute of Technology, a Ph.D. degree in Computer Science from Georgia State University, and B.S. (with Honors) and M.S. degrees both in Computer Science from Heilongjiang University. His current research interests include Data-driven Security and Privacy, AI Security and Big Data Analytics. He is a member of ACM, IEEE, and CCF and was the Membership Chair of the IEEE Student Branch at Georgia State University (2012-2013). He was a Research Intern at the IBM T. J. Watson Research Center. Shouling is the recipient of the 2012 Chinese Government Award for Outstanding Self-Financed Students Abroad.

Shouling Ji

Shouling Ji

Professor, Zhejiang University
Email: sji@zju.edu.cn

Shouling Ji

Shouling Ji

Professor, Zhejiang University
Email: sji@zju.edu.cn

Shouling Ji is a ZJU 100-Young Professor in the College of Computer Science and Technology at Zhejiang University and a Research Faculty in the School of Electrical and Computer Engineering at Georgia Institute of Technology (Georgia Tech). He received a Ph.D. degree in Electrical and Computer Engineering from Georgia Institute of Technology, a Ph.D. degree in Computer Science from Georgia State University, and B.S. (with Honors) and M.S. degrees both in Computer Science from Heilongjiang University. His current research interests include Data-driven Security and Privacy, AI Security and Big Data Analytics. He is a member of ACM, IEEE, and CCF and was the Membership Chair of the IEEE Student Branch at Georgia State University (2012-2013). He was a Research Intern at the IBM T. J. Watson Research Center. Shouling is the recipient of the 2012 Chinese Government Award for Outstanding Self-Financed Students Abroad.

Program Chairs

Kefeng Deng (Alibaba Group) Jun Zhu (Tsinghua University)

Hui Xue (Alibaba Group) Weiming Zhang (USTC)

Tao Xiong (Ant Financial) Ziqiang Feng (CMU)

Yuan He (Alibaba Group) Wei Xu (Ant Financial)

Yuhong Li (Alibaba Group) Liang Shi (Dingxiang Ltd Inc.)

Yuefeng Chen (Alibaba Group) Da Chen (Alibaba Group)

Kaizhu Huang (Xi’an Jiaotong-Liverpool University) Qi Wu (University of Adelaide)

Ye Liu (National University of Singapore) Yu Qi (Zhejiang University)

Program Chairs

Kefeng Deng (Alibaba Group)
Hui Xue (Alibaba Group)
Tao Xiong (Ant Financial)
Yuan He (Alibaba Group)
Yuhong Li (Alibaba Group)
Yuefeng Chen (Alibaba Group)
Da Chen (Alibaba Group)
Yu Qi (Zhejiang University)
Jun Zhu (Tsinghua University)
Weiming Zhang (USTC)
Ziqiang Feng (CMU)
Wei Xu (Ant Financial)
Liang Shi (Dingxiang Ltd Inc.)
Kaizhu Huang (Xi’an Jiaotong-Liverpool University)
Qi Wu (University of Adelaide)
Ye Liu (National University of Singapore)

Call for Papers

The AIBS workshop will discuss a broad variety of topics related to business security, including but are not restricted to:

  • Content-based security, e.g., spam detection, pornography detection etc.
  • Copyright violation detection
  • Phone-fraud detection
  • User authentication, e.g., biometric spoofing, defences and liveness detection etc.
  • Human-machine Behaviour Recognition, e.g., design and analysis of CAPTCHAs, botnet detection etc.
  • Phishing detection and prevention
  • Intrusion detection and response
  • Anomalous behaviour detection
  • Malware identification
  • Business security in social networks and online ecommerce
  • Big data and visualization analytics for business security
  • Security and privacy of business data

This year, we also welcome papers that address issues related to the AI security:

  • Attacks on machine learning systems
    • training time attacks (e.g., data poisoning)
    • test time attacks (e.g., adversarial examples, model stealing)
  • Detection of attacks on machine learning systems
  • Increasing robustness of machine learning systems
  • Explainable A.I.

We encourage participants to submit a paper (3-6 pages without references), describing work on one of the topics mentioned above. All submissions must be in English, include the author’s name(s), affiliation and email address. Please use the official guidelines to format your paper. For formatting guidelines, lateX styles and word template, check https://www.ijcai.org/authors_kit. All submissions can be made through https://easychair.org/conferences/?conf=aibs2019. For Post-proceedings, all the accepted papers of AIBS 2019 will be considered for publication by Springer in a multi-volume set.

Any questions may be directed to the workshop e-mail address: daniel.yuhong@alibaba-inc.com, yuefeng.chenyf@alibaba-inc.com.

Key Dates

Paper Submission Deadline
May 31th, 2019 11:59PM
Author Notification
June 10th, 2019
Camera Ready Version
June 20th, 2019
Workshop
August 10-12th, 2019

Key Dates

 

Paper Submission Deadline: May 31th, 2019 11:59PM

Author Notification: June 10th, 2019

Camera Ready Version: June 20th, 2019

Workshop: August 10-12th, 2019