A Game-Theoretic Approach for PMU Deployment Against False Data Injection Attacks
Phasor Measurement Units (PMUs) are used in the measurement, control and protection of power grids. However, deploying PMUs at every bus in a power system is prohibitively expensive, necessitating partial PMU placement that can ensure system observability with minimal units. One consequence of this economic approach is increased system vulnerability to False Data Injection Attacks (FDIAs). This paper proposes a zero-sum game-based approach to strategically place an additional PMU (following the initial optimal PMU deployment that ensures full observability) to bolster robustness against FDIAs by introducing redundancy in attack-susceptible areas. To compute the Nash equilibrium (NE) solution, we leverage a reinforcement learning algorithm that mitigates the need for complete knowledge of the opponent's actions. The proposed PMU deployment algorithm increases the detection rate of FDIA by 36% compared to benchmark algorithms.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Randomized Prediction Games for Adversarial Machine Learning
In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e.g., malware code is typically obfuscated using random strings or …
BIG-bench Machine LearningGeneral ClassificationHandwritten Digit RecognitionMalware Detection+1Async Control: Stress-testing Asynchronous Control Measures for LLM Agents
LLM-based software engineering agents are increasingly used in real-world development tasks, often with access to sensitive data or security-critical codebases. Such agents could intentionally sabotage these codebases if…
Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective
As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversight of the humans and institutions involved in their development and …
A Game-Theoretic Approach to Adversarial Linear Support Vector Classification
In this paper, we employ a game-theoretic model to analyze the interaction between an adversary and a classifier. There are two classes (i.e., positive and negative classes) to which data points can belong. The adversary…
ClassificationGeneral ClassificationA Shapley Value Solution to Game Theoretic-based Feature Reduction in False Alarm Detection
False alarm is one of the main concerns in intensive care units and can result in care disruption, sleep deprivation, and insensitivity of care-givers to alarms. Several methods have been proposed to suppress the false a…
General Classification