17 November 2021 in IEEE Transactions on Dependable and Secure Computing
Federated learning allows a large number of resource-constrained clients to train a globally-shared model together without sharing local data. These clients usually have only a few classes (categories) of data for training, where the data distribution is non-iid (not independent identically distributed). In this paper, we put forward the concept of category privacy for the first time to indicate which classes of data a client has, which is an important but ignored privacy goal in the federated learning with non-iid data. Although secure aggregation protocols are designed for federated learning to protect the input privacy of clients, we perform the first systematic study on category inference attack and demonstrate that these protocols cannot fully protect category privacy. We design a differential selection strategy and two de-noising approaches to achieve the attack goal successfully. In our evaluation, we apply the attack to non-iid federated learning settings with various datasets. On MNIST, CIFAR-10, AG\_news, and DBPedia datasets, our attack achieves >90% accuracy measured in F1-score in most cases. We further consider a possible detection method and propose two strategies to make the attack more inconspicuous.
13 September 2021 in IEEE Transactions on Industrial Informatics
The federated learning provides an effective solution to train collaborative models over a large scale of participated Industrial Internet of Things (IIoT) applications with the help of a global server, building an intelligent life. However, the federated learning is vulnerable to the backdoor attack from strong malicious participants. The backdoor attack is inconspicuous and may result in devastating consequences. To resist the attack on IIoT applications, we propose the federated backdoor filter defense that can identify backdoor inputs and restore the data to availability by the blur-label-flipping strategy. We build multiple filters with eXplainable AI models on the server and send them to clients randomly, preventing advanced attackers from evading the defense. Our backdoor filters show significant backdoor recognition with the accuracy up to 99%. After the implementation of the blur-label-flipping strategy, victim's local model on suspicious backdoor samples can achieve the accuracy up to 88%.
25 January 2022 in IEEE Transactions on Industrial Informatics
Big data, due to its promotion for industrial intelligence, has become the cornerstone of the Industry 4.0 era. Federated learning , proposed by Google, can effectively integrate data from different devices and different domains to train models under the premise of privacy preservation. Unfortunately, this new training paradigm faces security risks both on the client side and server side. This article proposes a new federated learning scheme to defend from client-side malicious uploads (e.g., backdoor attacks). In addition, we use cryptography techniques to prevent server-side privacy attacks (e.g., membership inference). The secure partial aggregation protocol we designed improves the privacy and robustness of federated learning. The experiments show that models can achieve high accuracy of over 90% with a proper upload proportion, while the accuracy of the backdoor attack decreased from 99.5% to 0% with the best result. Meanwhile, we prove that our protocol can disable privacy attacks.