DYNAMICS 2021 Call for Papers

The 2021 DYnamic and Novel Advances in Machine Learning and Intelligent Cyber Security (DYNAMICS) Workshop will be held virtually on Monday, December 10^th, 2021. The workshop will be co-located with the 2021 Annual Computer Security Applications Conference (ACSAC), held virtually.

Machine learning has become critical to the evolution and sustainability of cybersecurity. While the theoretical objectives and principles behind cybersecurity are still valid, traditional technologies that require humans in the loop to read log files, triage alerts, and harden devices are neither fast enough nor scalable enough to meet the demands of modern networks and attacks. While network traffic and devices have grown by orders of magnitude, the ability for operators to triage the resulting alerts has not.

The sophistication of threats has also increased substantially. Sophisticated zero-day attacks go undetected for months at a time. Attacks take place over extended periods, effectively outwaiting traditional intrusion detection technology. 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 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.

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The DYNAMICS Workshop invites submissions of original, previously unpublished technical papers, posters, and panels on research in machine learning and cybersecurity.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 2021 ACM Proceedings Template: https://www.acm.org/publications/proceedings-template, 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 emailed at dynamics.submissions@gmail.com.

Papers that have been accepted by the DYNAMICS workshop will be published in the workshop proceedings.

By submitting a paper 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.

Attacking and Defending Machine Learning-Based Systems, Models, and Data Sets

Trojan attacks on machine learning models
Attacking and defending ML supply chains
Attacking and defending autonomous systems and sensors
Trustworthy ML-based systems

Attacking and Defending Autonomous Vehicles and Autonomous Mobility

Attacks on autonomous vehicle autonomy stacks
Attacks, defenses, and deception in autonomous mobility
Machine learning-based techniques for protecting and disrupting autonomous systems
Detection of threats to autonomous systems

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

Trustworthy Analytics

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