An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching reconstruction and membership inference attacks. To defend such privacy attacks, many noises perturbation methods (like differential privacy or CountSketch matrix) have been widely designed. However, the strong defence ability and high learning accuracy of these schemes cannot be ensured at the same time, which will impede the wide application of FL in practice (especially for medical or financial institutions that require both high accuracy and strong privacy guarantee). To overcome this issue, in this paper, we propose an efficient model perturbation method for federated learning to defend reconstruction and membership inference attacks launched by curious clients. On the one hand, similar to the differential privacy, our method also selects random numbers as perturbed noises added to the global model parameters, and thus it is very efficient and easy to be integrated in practice. Meanwhile, the random selected noises are positive real numbers and the corresponding value can be arbitrarily large, and thus the strong defence ability can be ensured. On the other hand, unlike differential privacy or other perturbation methods that cannot eliminate the added noises, our method allows the server to recover the true gradients by eliminating the added noises. Therefore, our method does not hinder learning accuracy at all. Extensive experiments demonstrate that for both regression and classification tasks, our method achieves the same accuracy as non-private approaches and outperforms the state-ofthe-art related schemes. Besides, the defence ability of our method is significantly better than the state-of-the-art related defence schemes. Specifically, for the membership inference attack, our method achieves attack success rate (ASR) of around 50%, which is equivalent to blind guessing. However, the ASR of other defence methods is around 60%, which means that clients have a certain advantage to attack successfully compared with blind guessing. For the reconstruction attack, the ASR of our method is around X. Yang, Y. Feng, W. Fang and S. Xia are with