Attack Graph

Attack graphs visually represent potential attack paths within a system, aiding cybersecurity professionals in vulnerability assessment and threat modeling. Current research focuses on automating attack graph generation using large language models and graph neural networks, improving their accuracy and scalability, particularly for large, dynamic systems like Active Directories. This work also addresses the robustness of attack graphs and their underlying models against adversarial attacks, aiming to enhance the reliability and effectiveness of security analysis and proactive defense strategies. The resulting improvements in attack graph generation and analysis have significant implications for improving cybersecurity defenses and risk management.

Papers

November 6, 2022

Exposing Surveillance Detection Routes via Reinforcement Learning, Attack Graphs, and Cyber Terrain
Lanxiao Huang, Tyler Cody, Christopher Redino, Abdul Rahman, Akshay Kakkar, Deepak Kushwaha, Cheng Wang, Ryan Clark, Daniel Radke, Peter Beling, Edward Bowen
Reinforcement Learning Reinforcement Learning Algorithm Path Modeling Attack Graph

October 6, 2022

LGTBIDS: Layer-wise Graph Theory Based Intrusion Detection System in Beyond 5G
Misbah Shafi, Rakesh Kumar Jha, Sanjeev Jain
Graph Structure Intrusion Detection Intrusion Detection System Malicious Node Attack Graph Electromagnetic Signal Injection Attack

July 21, 2022

Knowledge-enhanced Black-box Attacks for Recommendations
Jingfan Chen, Wenqi Fan, Guanghui Zhu, Xiangyu Zhao, Chunfeng Yuan, Qing Li, Yihua Huang
Deep Learning Adversarial Attack Movie Recommendation New Attack Knowledge Enhancement Black Box Adversarial Attack Attack Graph

June 15, 2022

Robust Attack Graph Generation
Dennis Mouwen, Sicco Verwer, Azqa Nadeem
Learned Model Product Automaton Attack Graph Distilled Model Pseudo Victim AttackER Automaton Model

January 28, 2022

Discovering Exfiltration Paths Using Reinforcement Learning with Attack Graphs
Tyler Cody, Abdul Rahman, Christopher Redino, Lanxiao Huang, Ryan Clark, Akshay Kakkar, Deepak Kushwaha, Paul Park, Peter Beling, Edward Bowen
Reinforcement Learning Optimal Path Attack Graph Data Exfiltration

Attack Graph

Papers

Exposing Surveillance Detection Routes via Reinforcement Learning, Attack Graphs, and Cyber Terrain

LGTBIDS: Layer-wise Graph Theory Based Intrusion Detection System in Beyond 5G

Knowledge-enhanced Black-box Attacks for Recommendations

Robust Attack Graph Generation

Discovering Exfiltration Paths Using Reinforcement Learning with Attack Graphs