Adversary-aware LEarning techniques and trends in Cybersecurity (ALEC)

AAAI Fall Symposium

October 18-19, 2018 | Arlington, VA

ALEC'18 papers are now published as CEUR Workshop Proceedings Vol-2269.

Purpose and Scope

Machine learning-based intelligent systems have experienced a massive growth over the past few years, and are close to becoming ubiquitous in the technology surrounding our daily lives. However, a critical challenge in machine learning-based systems is their vulnerability to security attacks from malicious adversaries. The vulnerability of these systems is further aggravated as it is non-trivial to establish the authenticity of data used to train the system, and even innocuous perturbations to the training data can be used to manipulate the system’s behavior in unintended ways.

This symposium track proposes to address the overarching need towards making automated, machine learning-based systems more robust and resilient against adversarial attacks, so that humans can use them in a safe and sustained manner. Towards this end, the symposium will serve as a forum to discuss and disseminate existing issues, open challenges, and future research directions this topic. Discussions and ideas generated in the symposium will be used to determine a roadmap for adversarial learning while identifying immediate technological enablers and hurdles as well as a far-term vision for the field.

Topics of interest include, but are not limited to the following:

  • Adversary-aware Machine Learning - Reinforcement Learning, Lifelong Learning, Deep Learning
  • Generative Adversarial Networks
  • Adversary- aware Prediction, Forecasting and Decision Making Techniques
  • Game Theory and Game Playing to counter adversarial learning
  • Distributed, Multi-agent Systems
  • Adversarial Issues and Techniques for Cyber-Physical Systems, Adversarial Robotics
  • Operations Research related to Adversarial Learning
  • Applications of Adversarial Learning
  • Security Threats and Vulnerabilities of Adversarial Learning
  • Human factors and adversarial learning with human-in-the-loop

Program

October 18, 2018 (Thursday)

  • 9:00 - 9:30 Welcome and Introductions
  • 9:30 - 10:30 Keynote Talk: AI Canonical Architecture and Robust AI, David Martinez (Associate Division Head, Cyber Security and Information Sciences Division, MIT Lincoln Lab) Web
  • 10:30 - 11:00 Networking/Coffee break
  • 11:00 - 12:30 Session 1 (Chair: Raj Dasgupta)
    • 11:00 - 11:35 Static Malware Detection & Subterfuge: Quantifying the Robustness of Machine Learning and Current Anti-Virus, William Fleshman, Edward Raff*, Richard Zak, Mark McLean and Charles Nicholas
    • 11:35 - 12:10 Integrating Collaborative Cognitive Assistants Into Cybersecurity Operations Centers, Steve Meckl*, Gheorghe Tecuci, Dorin Marcu and Mihai Boicu
    • 12:10 - 12:30 Inefficiencies in Cyber-Security Exercises Life-Cycle: A Position Paper, Muhammad Mudassar Yamin* and Basel Katt
  • 12:30 - 2:00 Lunch break
  • 2:00 - 2:30 Paper Session 2 (Chair: Amitabh Mishra)
    • 2:00 - 2:30 Exploring Adversarial Examples in Malware Detection, Octavian Suciu*, Scott E. Coull and Jeffrey Johns
  • 2:30 - 3:30 Invited Talk: Naval Decision Superiority at the Tactical Level: Artificial Intelligence and Machine Learning Requirements, William Treadway (OPNAV N2/N6)
  • 3:35 - 4:00 Networking/Coffee break
  • 4:00 - 5:00 Paper Session 3 (Chair: Joseph Collins)
    • 4:00-4:30 Projecting Trouble: Light based Adversarial Attacks on Deep Learning Classifiers, Nicole Nichols* and Rob Jasper
    • 4:30- 5:00 Coordination-driven learning in multi-agent problem spaces, Sean L. Barton, Nicholas R. Waytowich and Derrik E. Asher*
  • 6:00 pm - 7:00 pm Reception (All Symposium Tracks)

October 19, 2018 (Friday)

9:00 - 10:30 Joint Session with AI in Government & Public Sector

    • 9:00 - 9: 10 Welcome Back
    • 9:10 - 9:40 Practical Defenses Against Adversarial Threats to AI, Matheiu Sinn (IBM)
    • 9:40 - 10:10 Tien Pham (Army Research Lab)
    • 10:10 - 10:30 Panel Discussion: Panelists: Mathieu Sinn, Tien Pham and Jerry Zhu
  • 10:30 -11:00 Networking/Coffee break
  • 11:00 - 12:00 Keynote Talk: An Optimal Control View of Adversarial Machine Learning, Xiaojin (Jerry) Zhu (Professor, Computer Science University of Wisconsin, Madison) Web
  • 12:00 - 12:30 Paper Session 4 (Chair: Ranjeev Mittu)
    • 12:00 - 12:30 An Artificial Coevolutionary Framework for Adversarial AI, Erik Hemberg and Unamay Oreilly*
  • 12:30- 2:00 Lunch break
  • 2:00 - 3:35 Paper Session 4 (contd.) (Chair: Ranjeev Mittu)
    • 2:00 - 2:35 Gray-box Techniques for Adversarial Text Generation, Prithviraj Dasgupta*, Joseph Collins and Anna Buhman
    • 2:35 - 3:05 Big Data and Deep Models Applied to Cyber Security Data Analysis, Ying Zhao*, Andrew Polk, Shaun Kallis, Lauren Jones, Riqui Schwamm and Tony Kendall
    • 3:05-3:35 Adversarial Training on Word-Char Embedding, Abebaw Tadesse and Joseph Collins*
  • 3:30 - 4:00 Networking/Coffee break
  • 4:00 - 5:00 Breakout sessions on Open Problems, Current Challenges and Future Roadmap for Adversarial AI in Cybersecurity
  • 5:00 - 5:30 Summary discussions from breakout session and wrap-up
  • 6:00 - 7:30 AAAI Plenary Talk (All Symposia)

TRAVEL & REGistration

The AAAI 2018 Fall Symposium Series will be held at the Westin Arlington Gateway in Arlington, VA. Registration and hotel details from AAAI are here.

Submission INSTRUCTIONS

Authors are invited to submit original research, visionary papers, works-in-progress and papers describing software, hardware tools and datasets on different aspects related to adversarial learning. All submissions will be peer-reviewed by the symposium program committee. At least one of the authors of accepted papers must present the paper at the symposium.

Papers should be formatted using AAAI Author Kit available here.

Papers should be submitted only through ALEC18 EasyChair Website.

Submissions are invited in the following categories:

  • Full Paper: 6-8 pages
  • Short Paper/Position Paper/Work-in-progress: 2-4 pages
  • Tools Paper (software, hardware and/or datasets relevant to adversarial learning): 2-3 pages

Accepted papers will be published as online proceedings on CEUR-WS.org in the form of technical reports. (ALEC'18 Proc Selected, high-quality papers will be considered for a special issue in a leading archival conference proceedings series/journal/magazine in the field of intelligent systems and cyber-security.

Important Dates

Paper (full and short) submission deadline: July 31 July 20

Paper notifications: August 17

Final camera-ready papers due: September 15 September 14

Registration deadline: September 21

Organizing Committee

  • Joseph Collins, US Naval Research Laboratory
  • Prithviraj (Raj) Dasgupta, University of Nebraska, Omaha
  • Ranjeev Mittu, US Naval Research Laboratory
  • Amitabh Mishra, US Army CERDEC
  • Krishnendu (Kris) Ghosh, Miami University of Ohio