arXiv cs.AI· Manoj Twarakavi, Venkata Sriram Siddhardh Nadendla·· 12 小时前AI 评分26
StratFL：用策略性联邦学习对抗隐蔽模型投毒攻击
StratFL: Countering Covert Model Poisoning Attacks with Strategic Federated Learning
AI 导读
StratFL 是一种针对联邦学习中隐蔽模型投毒（CMP）攻击的对抗搜索算法，将服务器与攻击者的交互建模为双方均无法观测对方动作的不完美重复博弈，并为服务器和攻击者分别设计了信念更新算法。在 MNIST 和 CIFAR-10 上的实验显示，StratFL 相比现有最优方法准确率提升 10%，并验证了信念更新算法在不同安全场景下的收敛性。
正文 · 原文
Abstract:Advanced persistent threats (APTs) are a major concern in federated learning (FL) deployments in critical sectors such as healthcare, and finance. Traditional defense mechanisms fail to contain APTs due to their intermittent attacking behavior. This paper addresses a specific type of APT called covert model poisoning (CMP) where the attacker intermittently injects poisoned model updates in a covert manner. The interaction between the FL server and a CMP attacker is modeled as an imperfect repeated game where both players cannot observe each other's actions. A novel adversarial search algorithm called StratFL is designed alongside novel belief update algorithms at both the server and adversary. Experiments are designed using MNIST and CIFAR-10 datasets to evaluate and compare StratFL's performance against state-of-the-art methods. Empirical convergence of belief update algorithms is demonstrated across various security vignettes. At the same time, StratFL is found to exhibit an improved accuracy of 10% compared to state-of-the-art methods.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT) |
| Cite as: | arXiv:2610.22626 [cs.CR] |
| (or arXiv:2610.22626v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22626 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Manoj Twarakavi [view email]
[v1]
Thu, 15 Oct 2026 20:27:44 UTC (162 KB)
来源：arXiv cs.AI · arxiv.org