Models and Framework for Adversarial Attacks on Complex Adaptive Systems
This work addresses security vulnerabilities in complex adaptive systems, which is a foundational problem for fields like infrastructure and defense, though it appears incremental as it builds on existing adversarial attack concepts.
The paper tackles the problem of adversarial attacks on Complex Adaptive Systems (CAS) by introducing modeling approaches and a reinforcement learning framework for simulation and analysis, demonstrating its performance through three real-world case studies including power grids and terrorist organizations.
We introduce the paradigm of adversarial attacks that target the dynamics of Complex Adaptive Systems (CAS). To facilitate the analysis of such attacks, we present multiple approaches to the modeling of CAS as dynamical, data-driven, and game-theoretic systems, and develop quantitative definitions of attack, vulnerability, and resilience in the context of CAS security. Furthermore, we propose a comprehensive set of schemes for classification of attacks and attack surfaces in CAS, complemented with examples of practical attacks. Building on this foundation, we propose a framework based on reinforcement learning for simulation and analysis of attacks on CAS, and demonstrate its performance through three real-world case studies of targeting power grids, destabilization of terrorist organizations, and manipulation of machine learning agents. We also discuss potential mitigation techniques, and remark on future research directions in analysis and design of secure complex adaptive systems.