Jakob Nyber, Pontus Johnson (KTH Royal Institute of Technology)

We implemented and evaluated an automated cyber defense agent. The agent takes security alerts as input and uses reinforcement learning to learn a policy for executing predefined defensive measures. The defender policies were trained in an environment intended to simulate a cyber attack. In the simulation, an attacking agent attempts to capture targets in the environment, while the defender attempts to protect them by enabling defenses. The environment was modeled using attack graphs based on the Meta Attack Language language. We assumed that defensive measures have downtime costs, meaning that the defender agent was penalized for using them. We also assumed that the environment was equipped with an imperfect intrusion detection system that occasionally produces erroneous alerts based on the environment state. To evaluate the setup, we trained the defensive agent with different volumes of intrusion detection system noise. We also trained agents with different attacker strategies and graph sizes. In experiments, the defensive agent using policies trained with reinforcement learning outperformed agents using heuristic policies. Experiments also demonstrated that the policies could generalize across different attacker strategies. However, the performance of the learned policies decreased as the attack graphs increased in size.

View More Papers

Investigating User Behaviour Towards Fake News on Social Media...

Yasmeen Abdrabou (University of the Bundeswehr Munich), Elisaveta Karypidou (LMU Munich), Florian Alt (University of the Bundeswehr Munich), Mariam Hassib (University of the Bundeswehr Munich)

Read More

Drone Security and the Mysterious Case of DJI's DroneID

Nico Schiller (Ruhr-Universität Bochum), Merlin Chlosta (CISPA Helmholtz Center for Information Security), Moritz Schloegel (Ruhr-Universität Bochum), Nils Bars (Ruhr University Bochum), Thorsten Eisenhofer (Ruhr University Bochum), Tobias Scharnowski (Ruhr-University Bochum), Felix Domke (Independent), Lea Schönherr (CISPA Helmholtz Center for Information Security), Thorsten Holz (CISPA Helmholtz Center for Information Security)

Read More

WIP: Towards the Practicality of the Adversarial Attack on...

Chen Ma (Xi'an Jiaotong University), Ningfei Wang (University of California, Irvine), Qi Alfred Chen (University of California, Irvine), Chao Shen (Xi'an Jiaotong University)

Read More

An Exploratory study of Malicious Link Posting on Social...

Muhammad Hassan, Mahnoor Jameel, Masooda Bashir (University of Illinois at Urbana Champaign)

Read More