Defending Distributed Systems Against Adversarial Attacks: Consensus, Consensusbased Learning, and Statistical Learning

Brief Biography: I am a postdoc in the Computer Sci- ence and Arti cial Intelligence Laboratory (CSAIL) at MIT, hosted by Professor Nancy Lynch. She received a Ph.D. in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign in 2017, supervised by Pro- fessor Nitin H. Vaidya. Her research intersects distributed systems, learning, security, and brain computing. She was the runner-up for the Best Student Paper Award at DISC 2016, and she received the 2015 Best Student Paper Award at SSS 2015. She received UIUC's Sundaram Seshu Interna- tional Student Fellowship for 2016, and was invited to par- ticipate in Rising Stars in EECS (2018). She has served on TPC for several conferences including ICDCS and ICDCN.

[1]  LynchNancy,et al.  Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory , 2019 .

[2]  Lili Su,et al.  Finite-Time Guarantees for Byzantine-Resilient Distributed State Estimation With Noisy Measurements , 2018, IEEE Transactions on Automatic Control.

[3]  Andrzej Pelc,et al.  Dissemination of Information in Communication Networks - Broadcasting, Gossiping, Leader Election, and Fault-Tolerance , 2005, Texts in Theoretical Computer Science. An EATCS Series.

[4]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[5]  Nitin H. Vaidya,et al.  Byzantine vector consensus in complete graphs , 2013, PODC '13.

[6]  Nitin H. Vaidya,et al.  Multi-agent optimization in the presence of Byzantine adversaries: Fundamental limits , 2016, 2016 American Control Conference (ACC).

[7]  Rachid Guerraoui,et al.  Byzantine-Tolerant Machine Learning , 2017, ArXiv.

[8]  Nitin H. Vaidya,et al.  Fault-Tolerant Multi-Agent Optimization: Optimal Iterative Distributed Algorithms , 2016, PODC.

[9]  Maurice Herlihy,et al.  Multidimensional approximate agreement in Byzantine asynchronous systems , 2013, STOC '13.

[10]  Kannan Ramchandran,et al.  Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning , 2018, ICML.

[11]  Shreyas Sundaram,et al.  Distributed Function Calculation via Linear Iterative Strategies in the Presence of Malicious Agents , 2011, IEEE Transactions on Automatic Control.

[12]  Nitin H. Vaidya,et al.  Byzantine-Resilient Multiagent Optimization , 2021, IEEE Transactions on Automatic Control.

[13]  Nancy A. Lynch,et al.  Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits , 2019, Neural Computation.

[14]  Lili Su,et al.  Securing Distributed Gradient Descent in High Dimensional Statistical Learning , 2018, Proc. ACM Meas. Anal. Comput. Syst..

[15]  Alexander V. Nazin,et al.  Algorithms of Robust Stochastic Optimization Based on Mirror Descent Method , 2019, Automation and Remote Control.

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

[17]  Lili Su,et al.  On Learning Over-parameterized Neural Networks: A Functional Approximation Prospective , 2019, NeurIPS.

[18]  Indranil Gupta,et al.  Generalized Byzantine-tolerant SGD , 2018, ArXiv.

[19]  Nancy A. Lynch,et al.  Ant-Inspired Dynamic Task Allocation via Gossiping , 2017, SSS.

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

[21]  Leslie Lamport,et al.  The Byzantine Generals Problem , 1982, TOPL.

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

[23]  Ali Jadbabaie,et al.  Non-Bayesian Social Learning , 2011, Games Econ. Behav..

[24]  Nitin H. Vaidya,et al.  Non-Bayesian Learning in the Presence of Byzantine Agents , 2016, DISC.

[25]  Nancy A. Lynch,et al.  Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory , 2019, SIGMETRICS.

[26]  Nancy A. Lynch,et al.  Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory , 2018, Proc. ACM Meas. Anal. Comput. Syst..

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