arXiv:1906.02872
Mixed Strategy Game Model Against Data Poisoning Attacks
원문 초록
In this paper we use game theory to model poisoning attack scenarios. We prove the non-existence of pure strategy Nash Equilibrium in the attacker and defender game. We then propose a mixed extension of our game model and an algorithm to approximate the Nash Equilibrium strategy for the defender. We then demonstrate the effectiveness of the mixed defence strategy generated by the algorithm, in an experiment.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense
Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey
토론
이 논문과 연결된 포럼 글이 아직 없습니다.