AI Planning for Cyber Red-Teaming




We are hiring!

As part of this project we are seeking a post-doctoral researcher with knowledge in one or more of:

  • AI planning, or more generally decision making, under uncertainty and partial observability;
  • analysis of on-line algorithms and problem complexity; and/or
  • knowledge engineering for planning.

The position is for up to 3 years. The starting salary is AUD 94,287 per year, plus 17% superannuation.

For questions and expressions of interest, please contact Patrik Haslum.

PhD and other student projects are also available.

Mounting "simulated" attacks on a networked systems in order to find their weaknesses - often known as "pentesting" or "red teaming" - is an important tool in cyber security evaluation and defense. The goal of this project is to automate some aspects of the red-teaming process, using AI planning techniques. Challenges in making this work are many: How to derive planning models from the information about security vulnerabilities that is available, and how to obtain realistic estimates of the information that is not? How to exploit the structure of the problem to achieve both scalable planning (making plans for networks with hundreds or thousands of hosts) while making realistic assumptions. Finally, many types of cyber attacks are not only technical but target people's and organisation's vulnerabilities. How to incorporate those in a planning model is one more open research question.


The project is funded by the Australian government through the NGTF, 2017-2022.


The project is a collaboration between the ANU Planning and Optimisation research group, the Australian Defense Science and Technology Group and Data61.

Updated:  1 November 2018/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing