Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
复制标题
DOI：
--
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Hongyi Wang;Kartik K. Sreenivasan;Shashank Rajput;Harit Vishwakarma;Saurabh Agarwal;Jy-yong Sohn;
中科院分区：
文献类型：
--
作者：
Hongyi Wang;Kartik K. Sreenivasan;Shashank Rajput;Harit Vishwakarma;Saurabh Agarwal;Jy-yong Sohn;
由于其去中心化的性质，联邦学习（FL）在训练过程中很容易受到后门形式的对抗性攻击。后门的目标是破坏训练模型在特定子任务上的性能（例如，将绿色汽车分类为青蛙）。文献中已经介绍了一系列 FL 后门攻击，以及防御它们的方法，目前是否可以定制 FL 系统以抵御后门是一个悬而未决的问题。在这项工作中，我们提供了相反的证据。我们首先确定，在一般情况下，对后门的鲁棒性意味着模型对对抗性示例的鲁棒性，这本身就是一个主要的开放问题。此外，假设一阶预言或多项式时间，不太可能检测 FL 模型中后门的存在。我们将理论结果与一系列新的后门攻击结合起来，我们将其称为边缘情况后门。边缘情况后门迫使模型对看似简单的输入进行错误分类，但这些输入不太可能成为训练或测试数据的一部分，即它们位于输入分布的尾部。我们解释了这些边缘情况后门如何导致令人讨厌的失败，并可能对公平性产生严重影响，并表明，通过对手一方的仔细调整，人们可以将它们插入到一系列机器学习任务中（例如图像分类、OCR、文本预测、情感分析）。
Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training. The goal of a backdoor is to corrupt the performance of the trained model on specific sub-tasks (e.g., by classifying green cars as frogs). A range of FL backdoor attacks have been introduced in the literature, but also methods to defend against them, and it is currently an open question whether FL systems can be tailored to be robust against backdoors. In this work, we provide evidence to the contrary. We first establish that, in the general case, robustness to backdoors implies model robustness to adversarial examples, a major open problem in itself. Furthermore, detecting the presence of a backdoor in a FL model is unlikely assuming first order oracles or polynomial time. We couple our theoretical results with a new family of backdoor attacks, which we refer to as edge-case backdoors. An edge-case backdoor forces a model to misclassify on seemingly easy inputs that are however unlikely to be part of the training, or test data, i.e., they live on the tail of the input distribution. We explain how these edge-case backdoors can lead to unsavory failures and may have serious repercussions on fairness, and exhibit that with careful tuning at the side of the adversary, one can insert them across a range of machine learning tasks (e.g., image classification, OCR, text prediction, sentiment analysis).