Adaptive Cyber Defense

Workshop Details

• Schedule: 16-18 August 2023

• Location: Florida Institute of Technology, Melbourne, Florida, USA

• Registration: ACD 2023 Workshop Registration 

• Submissions: adaptive.cyber.defense@gmail.com 

  1. 1. 1. 1. • • Submission deadline: 2 June 2023

                • Paper acceptance notification: 23 June 2023

                • Camera-ready deadline: 21 July 2023

                • Formatting guidelines, LaTeX styles, and Word template: https://www.ijcai.org/authors_kit 

Submissions are recommended to be 6-10 pages but are not to exceed 10 pages (total length, including references and appendices).  Submissions should be in the IJCAI-23 format and will be judged according to the chosen category, significance to the workshop, proposal quality, and clarity.  Accepted submissions will be published on arXiv.

About the ACD Workshop

The International Workshop on Adaptive Cyber Defense was organized to share research that explores unique applications of Artificial Intelligence (AI) and Machine Learning (ML) as foundational capabilities for the pursuit of adaptive cyber defense. The cyber domain cannot currently be reliably and effectively defended without extensive reliance on human experts. Skilled cyber defenders are in short supply and often cannot respond fast enough to cyber threats.

Building on recent advances in Artificial Intelligence (AI) and Machine Learning (ML) the Cyber defense research community has been motivated to develop new dynamic and sustainable defenses through adaptive cyber defense. The cyber domain cannot currently be reliably and effectively defended without extensive reliance on human experts.  Skilled cyber defenders are in short supply and often cannot respond fast enough to cyber threats.  With the growing adoption of AI and ML techniques to both cyber and non-cyber settings, there is an increasing need to bridge the critical gap between AI and Cyber research and practitioners.  We must accelerate our efforts to create semi-autonomous cyber defenses that can learn to recognize and respond to cyber attacks or discover and mitigate weaknesses in cooperation with other cyber operation systems and human experts. Furthermore, these defenses must be adaptive, and able to evolve over time to take into account changes in attacker behavior, benign changes in the systems, and expected drift in user behavior over time. The ACD Workshop will focus on sharing research that explores unique applications of AI and ML as an emerging technology underpinning foundational capabilities of adaptive cyber defense. The Workshop will be comprised of technical presentations, a panel discussion focused on open problems and potential research solutions, and lightning talks. This domain consists of challenging problems of critical importance to national and global security. Participation in this workshop will offer potentially unprecedented opportunities to stimulate research and innovation in this area.  

Topics of interest include (but are not limited to):

• Autonomous and semi-autonomous reasoning and response for cyber domains

• Human-machine teaming for adaptive defense systems

• Artificial intelligence (AI) and machine learning (ML) for adaptive cyber defense environments

• Reasoning and course of action (COA) decision making in cyber operations

• Predictive analytics for proactive stance to cyber threats and opportunities

• Cognitive modeling of cyber defenders and attackers

• Multi-agent and distributed AI solutions for semi-autonomous collaboration for cyber operations

• Automated intrusion detection and response, including AI additions to Security Orchestration, Automation and Incident Response (SOAR)

• Moving target defenses with adaptive (rather than random) strategies

• Command and control for automated cyber response

• Cyber simulation environments developed for testing and validation of AI techniques

• Realistic models of human behavior in cyber domains

• Explorations of problem similarities between cyber and non-cyber domains

• Adaptive cyber defense use cases and issues with adoption

• Customized defenses based on observed attacker behavior

• Generative AI cyber security use cases

Workshop Structure

This main objective of this workshop is to bring together both the research community and the government and industry communities to exchange experiences, discuss challenges and propose research directions. We can summarize the workshop activities as follows:

• Technical presentations: invited and accepted paper speakers will share their thoughts and experience on adaptive cyber defense

• Academic-Industry-Government research direction discussion: top researchers in the area from academic, industry and government will discuss the current and future challenges in this area

• Challenge problems: Academic challenge event results and announcement of new challenge

• Lightning talks: an opportunity for each ACD-2021 presenter to give a quick summary of their paper and provide any updates in person to the workshop

Workshop Structure

Wednesday, 16th August 2023

19:30 – 21:00 No-host Dinner (optional)

Thursday, 17th August 2023

08:30 – 09:30 Breakfast (included) and Registration

09:30 – 09:45 Welcome / Introductions / Agenda Overview 

09:45 – 10:55 Invited Keynote Talk – introduced by Marco Carvalho

• DARPA Cyber Agents for Security Testing and Learning Environments (CASTLE), Tejas Patel, Program Manager

10:55 – 11:10 Break with Refreshments

11:10 – 12:00 Paper Session – chaired by Mark Bilinski

• EIReLaND: Evaluating and Interpreting Reinforcement-Learning-based Network Defenses, Steven Cheung, Jared Claypoole, Prakhar Sharma, Vinod Yegneswaran, Ashish Gehani, Susmit Jha, John Emanuello, Ahmad Ridley

• On Autonomous Agents in a Cyber Defence Environment, Mitchell Kiely, David Bowman, Maxwell Standen, Christopher Moir

12:00 – 13:30 Lunch (included)

13:30 – 14:45 Paper Session – chaired by Damian Marriott

• Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning, Jacob Wiebe, Ranwa Al Mallah, Li Li

•  Adaptive Attack Detection in Text Classification: Leveraging Space Exploration Features for Text Sentiment Classification, Atefeh Mahdavi, Neda Keivandarian, Marco Carvalho

14:45 – 15:15 TTCP CAGE Challenge 3 Results and Challenge 4 -- Max Standen, DSTG

15:15 – 15:45 Break with Refreshments

15:45 – 16:45 Paper Session – chaired by Marco Carvalho

• Towards Autonomous Cyber Operation Agents: Exploring the Red Case, Li Li, Jean-Pierre S. El Rami, Ryan Kerr, Adrian Taylor, Grant Vandenberghe

• HoneyGAN Pots: A Deep Learning Approach for Generating Honeypots, Ryan Gabrys, Daniel Silva, Mark Bilinski

16:45 – 16:50 Break 

16:50 – 17:30 Tour – Center for Advanced Manufacturing and Innovative Design (CAMID)

17:30 – 18:45 Transportation to Reception

19:00 – 21:00 Reception at the Kennedy Space Center

21:00 – 22:00 Return to CAMID

Friday, 18th August 2023

08:30 – 09:30 Breakfast (included) and Registration

09:30 – 10:30 Invited Keynote Talk – introduced by Ahmad Ridley

• AI / ML / Reinforcement Learning applications to wireless and space communications systems, R. Chandramouli (Mouli), CEO Spectronn

10:30 – 10:45 Break with Refreshments

10:45 – 12:00 Panel Discussion – chaired by Ahmad Ridley

• Towards Autonomous Cyber-Defense: How Can AI/ML Enable Autonomous Mitigation of Current & Future Cyber-Attacks?

12:00 – 12:30 Summary and Wrap Up Session

Lunch (optional)

Co-Chairs/Organizing Committee

Prof. Marco Carvalho, Florida Institute of Technology, USA

Dr. Damian Marriott, Defence Science and Technology Group (Alumnus), Australia

Dr. Mark Bilinski, Naval Information Warfare Center Pacific, USA

Dr. Ahmad Ridley, Laboratory for Advanced Cybersecurity Research, USA

Contact

All questions about the workshop and submissions should be directed to: adaptive.cyber.defense@gmail.com