Distributed Computing

, Volume 32, Issue 4, pp 277–289 | Cite as

Defending non-Bayesian learning against adversarial attacks

  • Lili SuEmail author
  • Nitin H. Vaidya


This paper addresses the problem of non-Bayesian learning over multi-agent networks, where agents repeatedly collect partially informative observations about an unknown state of the world, and try to collaboratively learn the true state out of m alternatives. We focus on the impact of adversarial agents on the performance of consensus-based non-Bayesian learning, where non-faulty agents combine local learning updates with consensus primitives. In particular, we consider the scenario where an unknown subset of agents suffer Byzantine faults—agents suffering Byzantine faults behave arbitrarily. We propose two learning rules. In our learning rules, each non-faulty agent keeps a local variable which is a stochastic vector over the m possible states. Entries of this stochastic vector can be viewed as the scores assigned to the corresponding states by that agent. We say a non-faulty agent learns the underlying truth if it assigns one to the true state and zeros to the wrong states asymptotically.
  • In our first update rule, each agent updates its local score vector as (up to normalization) the product of (1) the likelihood of the cumulative private signals and (2) the weighted geometric average of the score vectors of its incoming neighbors and itself. Under reasonable assumptions on the underlying network structure and the global identifiability of the network, we show that all the non-faulty agents asymptotically learn the true state almost surely.

  • We propose a modified variant of our first learning rule whose complexity per iteration per agent is \(O(m^2 n \log n)\), where n is the number of agents in the network. In addition, we show that this modified learning rule works under a less restrictive network identifiability condition.


Distributed learning Byzantine agreement Fault-tolerance Adversary attacks Security 


  1. 1.
    Su, L., Vaidya, N.H.: Non-Bayesian learning in the presence of Byzantine agents. To appear in Proceedings of ACM Symposium on Distributed Computing (DISC) (2016)Google Scholar
  2. 2.
    Chamberland, J.-F., Veeravalli, V.V.: Decentralized detection in sensor networks. IEEE Trans. Signal Process. 51, 407–416 (2003)CrossRefGoogle Scholar
  3. 3.
    Gale, D., Kariv, S.: Bayesian learning in social networks. Games Econ. Behav. 45, 329–346 (2003)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Jadbabaie, A., Molavi, P., Sandroni, A., Tahbaz-Salehi, A.: Non-Bayesian social learning. Games Econ. Behav. 76, 210–225 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Tsitsiklis, J.: Decentralized detection by a large number of sensors. Math. Control Signals Syst. 1, 167–182 (1988)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Tsitsiklis, J.N.: Decentralized detection. In: Poor, H.V., Thomas, J.B. (eds.) Advances in Statistical Signal Processing. JAI Press, Greenwich (1993)Google Scholar
  7. 7.
    Varshney, P.K.: Distributed Detection and Data Fusion. Springer, Berlin (2012)Google Scholar
  8. 8.
    Wong, E., Hajek, B.: Stochastic Processes in Engineering Systems. Springer, Berlin (2012)zbMATHGoogle Scholar
  9. 9.
    Bajović, D., Jakovetić, D., Moura, J.M., Xavier, J., Sinopoli, B.: Large deviations performance of consensus+ innovations distributed detection with non-Gaussian observations. IEEE Trans. Signal Process. 60(11), 5987–6002 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Cattivelli, F.S., Sayed, A.H.: Distributed detection over adaptive networks using diffusion adaptation. IEEE Trans. Signal Process. 59(5), 1917–1932 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Jakovetić, D., Moura, J.M., Xavier, J.: Distributed detection over noisy networks: large deviations analysis. IEEE Trans. Signal Process. 60(8), 4306–4320 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Jadbabaie, A., Molavi, P., Tahbaz-Salehi, A.: Information heterogeneity and the speed of learning in social networks. Columbia Business School Research Paper (13-28) (2013)Google Scholar
  13. 13.
    Nedić, A., Olshevsky, A., Uribe, C.A.: Nonasymptotic convergence rates for cooperative learning over time-varying directed graphs. arXiv preprint arXiv:1410.1977 (2014)
  14. 14.
    Rad, K.R., Tahbaz-Salehi, A.: Distributed parameter estimation in networks. In: IEEE Conference on Decision and Control (CDC), pp. 5050–5055. IEEE (2010)Google Scholar
  15. 15.
    Shahrampour, S., Jadbabaie, A.: Exponentially fast parameter estimation in networks using distributed dual averaging. In: IEEE Conference on Decision and Control (CDC), pp. 6196–6201. IEEE (2013)Google Scholar
  16. 16.
    Lalitha, A., Sarwate, A., Javidi, T.: Social learning and distributed hypothesis testing. In 2014 IEEE International Symposium on Information Theory (ISIT), pp. 551–555, June 2014. Extended version at arXiv:1410.4307
  17. 17.
    Shahrampour, S., Rakhlin, A., Jadbabaie, A.: Finite-time analysis of the distributed detection problem. arXiv preprint arXiv:1512.09311 (2015)
  18. 18.
    Shahrampour, S., Rakhlin, A., Jadbabaie, A.: Distributed detection: finite-time analysis and impact of network topology. arXiv preprint arXiv:1409.8606 (2014)
  19. 19.
    Molavi, P., Tahbaz-Salehi, A., Jadbabaie, A.:. Foundations of non-Bayesian social learning. Columbia Business School Research Paper No. 15-95. SSRN: or (2017)
  20. 20.
    Olfati-Saber, R., Franco, E., Frazzoli, E., Shamma, J.: Belief consensus and distributed hypothesis testing in sensor networks. In: Networked Embedded Sensing and Control. Springer (2006)Google Scholar
  21. 21.
    Rahimian, M.A., Jadbabaie, M.A.: Learning without recall: a case for log-linear learning. IFAC-PapersOnLine 48(22), 46–51, ISSN 2405-8963 (2015).
  22. 22.
    Su, L., Vaidya, N.H.: Asynchronous distributed hypothesis testing in the presence of crash failures University of Illinois at Urbana-Champaign, technical report. arXiv:1606.03418 (2016)
  23. 23.
    Shahin, S., Ali, J.: An online optimization approach for multi-agent tracking of dynamic parameters in the presence of adversarial noise. In: American Control Conference (ACC). IEEE (2017)Google Scholar
  24. 24.
    Bedi, A.S., Sarma, P., Rajawat, K.: Adversarial multi-agent target tracking with inexact online gradient descent. arXiv preprint arXiv:1710.05133 (2017)
  25. 25.
    Peaseć, M., Shostakć, R., Lamport, L.: Reaching agreement in the presence of faults. J. ACM 27(2), 228–234 (1980)MathSciNetCrossRefGoogle Scholar
  26. 26.
    Dolev, D., Lynch, N.A., Pinter, S.S., Stark, E.W., Weihl, W.E.: Reaching approximate agreement in the presence of faults. J. ACM 33(3), 499–516 (1986)MathSciNetCrossRefzbMATHGoogle Scholar
  27. 27.
    Fekete, A.D.: Asymptotically optimal algorithms for approximate agreement. Distrib. Comput. 4(1), 9–29 (1990)MathSciNetCrossRefGoogle Scholar
  28. 28.
    LeBlanc, H.J., Zhang, H., Sundaram, S., Koutsoukos, X.: Consensus of multi-agent networks in the presence of adversaries using only local information. In: Proceedings of the 1st International Conference on High Confidence Networked Systems, HiCoNS ’12, pp. 1–10, New York, NY, USA. ACM (2012)Google Scholar
  29. 29.
    Vaidya, N.H.: Iterative byzantine vector consensus in incomplete graphs. In: Distributed Computing and Networking, pp. 14–28. Springer (2014)Google Scholar
  30. 30.
    Vaidya, N.H., Tseng, L., Liang, G.: Iterative approximate byzantine consensus in arbitrary directed graphs. In: Proceedings of the 2012 ACM Symposium on Principles of Distributed Computing, pp. 365–374. ACM (2012)Google Scholar
  31. 31.
    Mendes, H., Herlihy, M.: Multidimensional approximate agreement in Byzantine asynchronous systems. In: Proceedings of the Forty-Fifth Annual ACM Symposium on Theory of Computing, STOC ’13, pp. 391–400, New York, NY, USA. ACM (2013)Google Scholar
  32. 32.
    Su, L., Vaidya, N.H.: Reaching approximate byzantine consensus with multi-hop communication. In: Proceedings of International Symposium on Stabilization, Safety, and Security of Distributed Systems (SSS) (2015)Google Scholar
  33. 33.
    Lynch, N.A.: Distributed Algorithms. Morgan Kaufmann Publishers Inc., San Francisco (1996)zbMATHGoogle Scholar
  34. 34.
    Vaidya, N.H., Garg, V.K.: Byzantine vector consensus in complete graphs. In: Proceedings of the 2013 ACM Symposium on Principles of Distributed Computing, pp. 65–73. ACM (2013)Google Scholar
  35. 35.
    Perles, M.A., Sigron, M.: A generalization of Tverberg’s theorem. arXiv:0710.4668 (2007)
  36. 36.
    Hajnal, J., Bartlett, M.: Weak ergodicity in non-homogeneous markov chains. In: Mathematical Proceedings of the Cambridge Philosophical Society, vol. 54, pp. 233–246. Cambridge University Press, Cambridge (1958)Google Scholar
  37. 37.
    Wolfowitz, J.: Products of indecomposable, aperiodic, stochastic matrices. In: Proceedings of the American Mathematical Society, pp. 733–737. JSTOR (1963)Google Scholar
  38. 38.
    Vaidya, N.H.: Matrix representation of iterative approximate Byzantine consensus in directed graphs. arXiv:1203.1888 (2012)

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Massachusetts Institute of TechnologyCambridgeUSA
  2. 2.University of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations