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

Browser Permission Mechanisms Demystified

Kazuki Nomoto (Waseda University), Takuya Watanabe (NTT Social Informatics Laboratories), Eitaro Shioji (NTT Social Informatics Laboratories), Mitsuaki Akiyama (NTT Social Informatics Laboratories), Tatsuya Mori (Waseda University/NICT/RIKEN AIP)

Read More

Death By A Thousand COTS: Disrupting Satellite Communications using...

Frederick Rawlins, Richard Baker and Ivan Martinovic (University of Oxford) Presenter: Frederick Rawlins

Read More

MetaWave: Attacking mmWave Sensing with Meta-material-enhanced Tags

Xingyu Chen (University of Colorado Denver), Zhengxiong Li (University of Colorado Denver), Baicheng Chen (University of California San Diego), Yi Zhu (SUNY at Buffalo), Chris Xiaoxuan Lu (University of Edinburgh), Zhengyu Peng (Aptiv), Feng Lin (Zhejiang University), Wenyao Xu (SUNY Buffalo), Kui Ren (Zhejiang University), Chunming Qiao (SUNY at Buffalo)

Read More

A Preliminary Study on Using Large Language Models in...

Kumar Shashwat, Francis Hahn, Xinming Ou, Dmitry Goldgof, Jay Ligatti, Larrence Hall (University of South Florida), S. Raj Rajagoppalan (Resideo), Armin Ziaie Tabari (CipherArmor)

Read More