First IEEE International Workshop on Adapting Data Mining for Security 2018

Singapore, November 17th, 2018

IEEE ADMiS Workshop co-located with IEEE International Conference on Data Mining (ICDM) 2018

Description

A half-day workshop on Adapting Data Mining for Security (ADMiS) to be held in Singapore in conjunction with the IEEE International Conference on Data Mining 2018. This workshop will address the research and educational efforts in which analytical techniques from data mining and machine learning, are applied to solve security and privacy challenges, and the security and privacy considerations involved in applying them to those challenges.

Increasingly, sophisticated techniques from data mining, and machine learning are being applied to challenges in security and privacy fields. However, experts from these areas have no high-visibility medium at a premier Data Mining conference such as ICDM, where they can meet and exchange ideas so that strong collaborations can emerge, and cross-fertilization of these areas can occur. Moreover, current courses and curricula in security do not sufficiently emphasize background in these areas and students in security are not emerging with deep knowledge of these topics. Hence, we propose a workshop that will address the research and development efforts in which analytical techniques from machine learning, data mining, are applied to solve security challenges. Submissions of papers related to methodology, design, techniques and new directions for security that make significant use of data mining and machine learning are welcome. Furthermore, submissions on educational topics and systems in the intersection of security and data mining are also highly encouraged.

The workshop will focus on, but not limited to, the following areas:

    • Data Mining techniques for security
    • Machine learning for security
    • Applications of AI to security
    • Inference Control
    • Privacy-preserving data mining
    • Security of machine learning
    • Security of data mining
    • Case studies
    • Educational topics and courses.

Plan

The half-day workshop is planned for November, 2018, with a keynote session, a technical session, a session /panel discussion on security education, future directions. The keynote speech will be delivered by a well-known researcher in the intersection of data mining and security.

ADMiS Workshop Timing:

  • 1:20 P.M. to 5:30 P.M. with a coffee break from 3:10 P.M. to 3:30 P.M.

Important Dates

    • Paper submission deadline: August 7, 2018 August 21, 2018 (11:59 P.M. PDT)
    • Author notification: September 9, 2018
    • Camera Ready deadline: September 15, 2018


Accepted Papers:

Below are the list of accepted full and short papers in no particular order. We have accepted 4 full and 5 short papers for ADMiS 2018.

Each full paper presentation is 25 mins (20 mins for presentation + 5 mins for Q&A). Each short paper is a total of 15 mins for presentation (10 mins for presentation + 5 mins for Q&A) .

Accepted Full Papers:

  • Unsupervised scanning behavior detection based on distribution of network traffic features using robust autoencoders - Gaku Kotani (University of Tokyo) and Yuji Sekiya (University of Tokyo)
  • Anomaly-based Insider Threat Detection using Deep Autoencoders - Liu Liu (Swinburne Univ. Of Technology), Olivier De Vel (Defense Science and Technology Group), Chao Chen (Swinburne Univ. Of Technology), Jun Zhang (Swinburne Univ. Of Technology), and Yang Xiang (Swinburne Univ. Of Technology)
  • Performance Evaluation of Features and Clustering Algorithms for Malware - Houtan Faridi (University of Houston), Srivathsan Srinivasagopalan (AlienVault/AT&T), and Rakesh Verma (University of Houston)
  • Selective Graph Attention Networks for Account Takeover Detection - Jialing Tao (Alibaba Inc.), Hui Wang (Alibaba Inc.), and Tao Xiong (Alibaba Inc.)

Accepted Short Papers:

  • Feature Engineering for Detecting Compromises in Enterprise Log Data - Jiayi Duan (U. Illinois), Ziheng Zeng (U. Illinois), Alina Oprea (U. Illinois), and Shobha Vasudevan (U. Illinois)
  • Preserving Differential Privacy and Utility of Non-Stationary Data Streams - Michael Khavkin (Ben-Gurion University of the Negev, Israel) and Mark Last (Ben-Gurion University of the Negev, Israel)
  • Time is of the Essence: Machine Learning-based Intrusion Detection in Industrial Time Series Data - Simon Duque Anton (German Research Center for Artificial Intelligence), Lia Ahrens (German Research Center for Artificial Intelligence), Daniel Fraunholz (German Research Center for Artificial Intelligence), and Hans Dieter Schotten (German Research Center for Artificial Intelligence)
  • Python Source Code De-Anonymization Using Nested Bigrams - Pegah Hozhabrierdi (Syracuse University), Dunai Fuentes Hitos (Matilock, Inc), and Chilukuri Mohan (Syracuse University)
  • Phishing Email Detection Using Robust NLP Techniques - Gal Egozi (University of Houston) and Rakesh Verma (University of Houston)

Submission

All submissions must describe original research, not published nor currently under review for another workshop, conference, or journal. All papers must be submitted electronically via the ICDM system: Submission link

All the submissions should follow the same format and page limit as ICDM regular submission (max 10 pages). Detailed layout guidelines are the same as recommended in http://icdm2018.org/calls/call-for-papers/

NOTE regarding Page Limit of Submissions:

1. The page limit should be at least: Short papers (4 pages) and long papers (8 pages)

2. Papers with more than 8 pages will need to pay extra page fee. The max page allowed is 10 pages.

3. The norm for ICDM workshop papers is 10 pages (2 extra page fee). This is probably because ICDM regular paper submission can choose to automatically go to workshop submissions if rejected.

Submission implies the willingness of at least one author to attend the workshop and present the paper. Accepted papers will be included in the in the IEEE ICDM 2018 Workshops Proceedings volume published by IEEE Computer Society Press and will also be included in the IEEE Xplore Digital Library. Therefore, papers must not have been accepted for publication elsewhere or be under review for another workshop, conferences or journals.

The presenter must register for the workshop before the deadline for author registration. The accepted papers will be compiled in the workshop proceedings as either a regular paper or a poster paper. Extended versions of selected high-quality workshop papers will be invited to a special issue of Journal of Security and Communication Networks planned for 1st half of 2019 (guest-editors include Akbar Namin and Rakesh Verma).

Call for papers!