Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we demystify the inner workings of existing (targeted) attacks. We provide new insights into why these attacks are possible and why a definitive solution to FL robustness is challenging. We show that the need for ML algorithms to memorize tail data has significant implications for FL integrity. This phenomenon has largely been studied in the context of privacy; our analysis sheds light on its implications for ML integrity. We show that certain classes of severe attacks can be mitigated effectively by enforcing constraints such as norm bounds on clients' updates. We investigate how to efficiently incorporate these constraints into secure FL protocols in the single-server setting. Based on this, we propose RoFL, a new secure FL system that extends secure aggregation with privacy-preserving input validation. Specifically, RoFL can enforce constraints such as $L_2$ and $L_\infty$ bounds on high-dimensional encrypted model updates.
翻译:尽管近年来我们目睹了许多攻击,暴露了联邦学习联合会(FL)的严重弱点,但仍然缺乏对这些攻击的哪些原因和如何有效减轻这些攻击的全面理解。在这项工作中,我们解开现有(目标)攻击的内部运作方式的神秘性。我们对这些攻击之所以可能,以及为什么最终解决FL的稳健性是具有挑战性的提供了新的见解。我们表明,ML算法对记住尾部数据的必要性对FL的完整性有着重大影响。这一现象大部分是在隐私背景下研究的;我们的分析揭示了这些攻击对ML完整性的影响。我们表明,通过对客户更新的规范约束等限制,可以有效地减轻某些类型的严重攻击。我们调查如何将这些限制有效地纳入单一服务器的安全FL协议。在此基础上,我们提议建立新的安全FLL系统,以保密的投入验证方式扩大安全集合。具体地说,RoLLL可以对高维值的加密模型进行约束,例如$L_2美元和$L ⁇ infty。