Security Game

Security games model strategic interactions between defenders and attackers, aiming to optimize resource allocation for minimizing losses from attacks. Current research focuses on extending these models to handle multiple defenders with diverse schedules, incorporating realistic human attacker behaviors (including cognitive biases and multi-step manipulation), and leveraging machine learning techniques like reinforcement learning and large language models to improve both attack and defense strategies. These advancements are significant for improving real-world cybersecurity, particularly in large-scale network security and resource protection scenarios, by providing more effective and efficient defense strategies against increasingly sophisticated attacks.

Papers

November 7, 2024

Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging
Rui Luo, Jie Bao, Zhixin Zhou, Chuangyin Dang
Adversarial Attack Adversarial Robustness Medical Imaging Adversarial Environment Security Game Robust Conformal Prediction

March 26, 2024

Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games
Yikuan Yan, Yaolun Zhang, Keman Huang
Reinforcement Learning Expert Knowledge Reinforcement Learning Agent LLM Policy Security Game Pre Trained Reinforcement Learning

November 28, 2023

Multi-defender Security Games with Schedules
Zimeng Song, Chun Kai Ling, Fei Fang
Task Scheduling Security Game Multiple Defender Heterogeneous Zero Day Attack Stackelberg Security Game

August 23, 2023

Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
Maria Rigaki, Ondřej Lukáš, Carlos A. Catania, Sebastian Garcia
Multi Agent Scenario Reinforcement Learning Environment Security Game Net CAGE Cybersecurity Environment

June 3, 2023

Learning to Defend by Attacking (and Vice-Versa): Transfer of Learning in Cybersecurity Games
Tyler Malloy, Cleotilde Gonzalez
LeArning Abstract Formality Transfer Human Decision Cognitive Bias Adversarial Behavior Human Bias Cyber Defense Security Game

March 28, 2023

Scaling Multi-Objective Security Games Provably via Space Discretization Based Evolutionary Search
Yu-Peng Wu, Hong Qian, Rong-Jun Qin, Yi Chen, Aimin Zhou
Payoff Function Evolutionary Search Evolutionary Multiobjective Security Game Heterogeneous Zero Day Attack

December 8, 2022

Simulation of Attacker Defender Interaction in a Noisy Security Game
Erick Galinkin, Emmanouil Pountourakis, John Carter, Spiros Mancoridis
Simulation Study Full Observability Pseudo Victim AttackER Security Game Cybersecurity Environment

November 9, 2022

Interpretable Deep Reinforcement Learning for Green Security Games with Real-Time Information
Vishnu Dutt Sharma, John P. Dickerson, Pratap Tokekar
Reinforcement Learning Deep Reinforcement Learning Real Time State Representation Security Game

April 29, 2022

Evolutionary Approach to Security Games with Signaling
Adam Żychowski, Jacek Mańdziuk, Elizabeth Bondi, Aravind Venugopal, Milind Tambe, Balaraman Ravindran
Reinforcement Learning Evolutionary Computation Abnormal Signal Evolutionary Approach Security Game Sensor Attack

April 26, 2022

Mixed Strategies for Security Games with General Defending Requirements
Rufan Bai, Haoxing Lin, Xinyu Yang, Xiaowei Wu, Minming Li, Weijia Jia
Adversarial Attack Security Game Stackelberg Security Game

February 28, 2022

Anti-Malware Sandbox Games
Sujoy Sikdar, Sikai Ruan, Qishen Han, Paween Pitimanaaree, Jeremy Blackthorne, Bulent Yener, Lirong Xia
Malware Detection Malicious User Defense Algorithm Security Game Sandbox Environment

February 27, 2022

The Art of Manipulation: Threat of Multi-Step Manipulative Attacks in Security Games
Thanh H. Nguyen, Arunesh Sinha
Strategic Manipulation Art Specific Information Threat Word Step Attack Security Game Multi Step Attack Stackelberg Security Game

January 17, 2022

NSGZero: Efficiently Learning Non-Exploitable Policy in Large-Scale Network Security Games with Neural Monte Carlo Tree Search
Wanqi Xue, Bo An, Chai Kiat Yeo
Deep Learning Monte Carlo Tree Search Security Game Fictitious Self Play

Security Game

Papers

Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging

Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games

Multi-defender Security Games with Schedules

Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments

Learning to Defend by Attacking (and Vice-Versa): Transfer of Learning in Cybersecurity Games

Scaling Multi-Objective Security Games Provably via Space Discretization Based Evolutionary Search

Simulation of Attacker Defender Interaction in a Noisy Security Game

Interpretable Deep Reinforcement Learning for Green Security Games with Real-Time Information

Evolutionary Approach to Security Games with Signaling

Mixed Strategies for Security Games with General Defending Requirements

Anti-Malware Sandbox Games

The Art of Manipulation: Threat of Multi-Step Manipulative Attacks in Security Games

NSGZero: Efficiently Learning Non-Exploitable Policy in Large-Scale Network Security Games with Neural Monte Carlo Tree Search