Attack-Resistant Federated Learning with Residual-based Reweighting

Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversarial attacks so that the global model may behave abnormally under attacks. To tackle this challenge, we present a novel aggregation algorithm with residual-based reweighting to defend federated learning. Our aggregation algorithm combines repeated median regression with the reweighting scheme in iteratively reweighted least squares. Our experiments show that our aggregation algorithm outperforms other alternative algorithms in the presence of label-flipping, backdoor, and Gaussian noise attacks. We also provide theoretical guarantees for our aggregation algorithm.

[1]  Vitaly Shmatikov,et al.  How To Backdoor Federated Learning , 2018, AISTATS.

[2]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[3]  Dan Alistarh,et al.  Byzantine Stochastic Gradient Descent , 2018, NeurIPS.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Vitaly Shmatikov,et al.  Exploiting Unintended Feature Leakage in Collaborative Learning , 2018, 2019 IEEE Symposium on Security and Privacy (SP).

[6]  Julia Kastner,et al.  Introduction to Robust Estimation and Hypothesis Testing , 2005 .

[7]  Ivan Beschastnikh,et al.  Mitigating Sybils in Federated Learning Poisoning , 2018, ArXiv.

[8]  Yang Song,et al.  Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning , 2018, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications.

[9]  Julian J. McAuley,et al.  Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering , 2016, WWW.

[10]  R. Wilcox.  Introduction to Robust Estimation and Hypothesis Testing , 1997 .

[11]  Christoph H. Lampert,et al.  Robust Learning from Untrusted Sources , 2019, ICML.

[12]  Giuseppe Ateniese,et al.  Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning , 2017, CCS.

[13]  H. Brendan McMahan,et al.  Differentially Private Learning with Adaptive Clipping , 2019, NeurIPS.

[14]  A. Siegel.  Robust regression using repeated medians , 1982 .

[15]  T. Minka.  Estimating a Dirichlet distribution , 2012 .

[16]  Dimitrios Pendarakis,et al.  Reaching Data Confidentiality and Model Accountability on the CalTrain , 2018, 2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN).

[17]  Kannan Ramchandran,et al.  Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates , 2018, ICML.

[18]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[19]  Emiliano De Cristofaro,et al.  LOGAN: Membership Inference Attacks Against Generative Models , 2017, Proc. Priv. Enhancing Technol..

[20]  Shie Mannor,et al.  Distributed Robust Learning , 2014, ArXiv.

[21]  Rui Zhang,et al.  A Hybrid Approach to Privacy-Preserving Federated Learning , 2018, Informatik Spektrum.

[22]  Tomas Mikolov,et al.  Bag of Tricks for Efficient Text Classification , 2016, EACL.

[23]  P. Holland,et al.  Robust regression using iteratively reweighted least-squares , 1977 .

[24]  Rachid Guerraoui,et al.  Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent , 2017, NIPS.

[25]  Blaine Nelson,et al.  Poisoning Attacks against Support Vector Machines , 2012, ICML.

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  Lili Su,et al.  Distributed Statistical Machine Learning in Adversarial Settings , 2017, Proc. ACM Meas. Anal. Comput. Syst..

[28]  Tassilo Klein,et al.  Differentially Private Federated Learning: A Client Level Perspective , 2017, ArXiv.

[29]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[30]  Lili Su,et al.  Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent , 2019, PERV.

[31]  Siddharth Garg,et al.  BadNets: Evaluating Backdooring Attacks on Deep Neural Networks , 2019, IEEE Access.

[32]  Qing Ling,et al.  RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasets , 2018, AAAI.

[33]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[34]  Sarvar Patel,et al.  Practical Secure Aggregation for Privacy-Preserving Machine Learning , 2017, IACR Cryptol. ePrint Arch..

[35]  Emiliano De Cristofaro,et al.  : Membership Inference Attacks Against Generative Models , 2018 .