About the DYNAMICS Workshop
The 2018 DYnamic and Novel Advances in Machine Learning and Intelligent Cyber Security (DYNAMICS) Workshop will be held on Monday, December 3rd and Tuesday, December 4th, 2018. The workshop will be co-located with the 2018 Annual Computer Security Applications Conference (ACSAC) at the Condado Plaza Hilton in San Juan, Puerto Rico, USA.
Machine learning has become critical to the evolution and sustainability of cyber security. While the theoretical objectives and principles behind cyber security are still valid, traditional technologies that require humans to read log files, triage alerts, and harden devices are neither sufficiently fast, nor scalable enough, to meet the demands of modern networks and attacks. While the volume of network data, and the number of devices on network, have grown by orders of magnitude, the rate at which humans can triage alerts has not.
The sophistication of threats has also increased substantially. Sophisticated zero-day attacks may go undetected for months at a time. Attack patterns may be engineered to take place over extended periods of time, making them very difficult for traditional intrusion detection technologies to detect. Worse, new attack tools and strategies can now be developed using adversarial machine learning techniques, requiring rapid co-evolution of defenses that match the speed and sophistication of machine learning-based offensive techniques.
This two-day workshop is intended to focus on novel applied and theoretical work that combines machine learning techniques such as reinforcement learning, adversarial machine learning, and deep learning with significant problems in cybersecurity. We consider both offensive and defensive applications of machine learning to security, with narrow topics grouped into six major topic areas presented over two days.
Technical Paper Submissions
The DYNAMICS Workshop invites submissions of original, previously unpublished technical papers, posters, and panels on research in machine learning and cybersecurity. Papers should be between 5 and 12 pages, and should use the 2017 ACM Proceedings Template: https://www.acm.org/publications/proceedings-templ… using the [sigconf, anonymous] options. Submissions will be evaluated using a standard peer review process. While authors may wish to align their submissions with one of the suggested topics below, submissions on other topics related to the workshop theme are welcome. Papers should be submitted through OpenConf, at https://www.acsac.org/2018/openconf-dynamics/.
Papers that have been accepted by the DYNAMICS workshop will be published in the workshop proceedings.
By submitting a paper, presentation, or panel to the DYNAMICS workshop, you agree that if your submission is accepted, one or more of the submission's authors will present the final version of the submission at the workshop.
Paper, panel, and poster submission deadline:
September 14th, 2018 (11:59 PM Eastern Time)
October 1st, 2018
Final PDF submission deadline:
October 19th, 2018 (11:59 PM Eastern Time)
Data Generation and Preparation:
• Data generation and labeling for machine learning-based security
• Feature extraction, weighting, and validation
• Data set validity
• Standardized data sets and data generation environments for scientific algorithm comparison
Feature Finding and Event Analysis:
• Detection of malicious code and events in large data sets
• Attack detection
• Insider threat detection
• Zero-day attack detection
• Large-scale network data analysis using machine learning
• Detection of threats with evolving behaviors or implementations
Adversarial Machine Learning for Cybersecurity:
• Training environments for adversarial machine learning-based security
• Training data poisoning: Adversarial ML attacks on training data
• Adversarial ML-derived strategies for attacking and defending networks
• Adversarial ML for deception
• Training humans and non-humans using adversarial ML
Machine Learning-Based Defense and Response:
• Automated responses to attacks
• Machine learning for autonomous and resilient cyber defense
• Machine learning-based cyber deception
• Automatic detection of zero-day attacks
• Machine learning-based vulnerability analysis
• Machine learning-driven access controls, security policies, etc.
• Counter-machine learning techniques, such as data poisoning and deception
• Real-time threat detection, decision making, and response
• Deep learning for automated recognition of novel threats or threat implementations
Machine Learning-Based Offensive Techniques:
• Machine learning-driven cyber offense
• Adversarial machine learning for network attacks
• Trust of data sources
• What makes an analytic trustworthy?
• Trust of analytic behavior
• Analytic validation
• Attacking analytics
• Manipulating analytic results with deception
• Trusted Execution Environment (TEE)-based analytics
How to Contact the Workshop Organizers
If you have questions related to the workshop, please e-mail them to email@example.com.
2018 DYNAMICS Workshop Organizers
• Dr. Michael Clifford, Noblis
• Dr. Bhavani Thuraisingham, UT Dallas
• Dr. Latifur Khan, UT Dallas
ACSAC Workshops Chair:
Harvey Rubinovitz, The MITRE Corporation