Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Detection of Malicious Agents in Social Learning (2403.12619v4)

Published 19 Mar 2024 in cs.SI, cs.MA, and eess.SP

Abstract: Non-Bayesian social learning is a framework for distributed hypothesis testing aimed at learning the true state of the environment. Traditionally, the agents are assumed to receive observations conditioned on the same true state, although it is also possible to examine the case of heterogeneous models across the graph. One important special case is when heterogeneity is caused by the presence of malicious agents whose goal is to move the agents toward a wrong hypothesis. In this work, we propose an algorithm that allows discovering the true state of every individual agent based on the sequence of their beliefs. In so doing, the methodology is also able to locate malicious behavior.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. A. Jadbabaie, P. Molavi, A. Sandroni, and A. Tahbaz-Salehi, “Non-Bayesian social learning,” Games and Economic Behavior, vol. 76, no. 1, pp. 210–225, 2012.
  2. X. Zhao and A. H. Sayed, “Learning over social networks via diffusion adaptation,” in Proc. Asilomar Conference on Signals, Systems and Computers, 2012, pp. 709–713.
  3. H. Salami, B. Ying, and A. H. Sayed, “Social learning over weakly connected graphs,” IEEE Trans. Signal and Information Processing over Networks, vol. 3, no. 2, pp. 222–238, 2017.
  4. A. Nedić, A. Olshevsky, and C. A. Uribe, “Fast convergence rates for distributed non-Bayesian learning,” IEEE Transactions on Automatic Control, vol. 62, no. 11, pp. 5538–5553, 2017.
  5. P. Molavi, A. Tahbaz-Salehi, and A. Jadbabaie, “Foundations of non-Bayesian social learning,” Columbia Business School Research Paper, no. 15-95, 2017.
  6. ——, “A theory of non-Bayesian social learning,” Econometrica, vol. 86, no. 2, pp. 445–490, 2018.
  7. V. Bordignon, V. Matta, and A. H. Sayed, “Adaptive social learning,” IEEE Transactions on Information Theory, vol. 67, no. 9, pp. 6053–6081, 2021.
  8. ——, “Partial information sharing over social learning networks,” IEEE Transactions on Information Theory, vol. 69, no. 3, pp. 2033–2058, 2023.
  9. A. Lalitha, T. Javidi, and A. D. Sarwate, “Social learning and distributed hypothesis testing,” IEEE Transactions on Information Theory, vol. 64, no. 9, pp. 6161–6179, 2018.
  10. Y. İnan, M. Kayaalp, E. Telatar, and A. H. Sayed, “Social learning under randomized collaborations,” in Proc. IEEE International Symposium on Information Theory (ISIT), 2022, pp. 115–120.
  11. J. Z. Hare, C. A. Uribe, L. Kaplan, and A. Jadbabaie, “Non-Bayesian social learning with uncertain models,” IEEE Transactions on Signal Processing, vol. 68, pp. 4178–4193, 2020.
  12. C. A. Uribe, A. Olshevsky, and A. Nedić, “Nonasymptotic concentration rates in cooperative learning–part i: Variational non-Bayesian social learning,” IEEE Transactions on Control of Network Systems, vol. 9, no. 3, pp. 1128–1140, 2022.
  13. D. Gale and S. Kariv, “Bayesian learning in social networks,” Games and Economic Behavior, vol. 45, no. 2, pp. 329–346, 2003.
  14. D. Acemoglu, M. A. Dahleh, I. Lobel, and A. Ozdaglar, “Bayesian learning in social networks,” The Review of Economic Studies, vol. 78, no. 4, pp. 1201–1236, 2011.
  15. J. Hkazla, A. Jadbabaie, E. Mossel, and M. A. Rahimian, “Bayesian decision making in groups is hard,” Operations Research, vol. 69, no. 2, pp. 632–654, 2021.
  16. M. G. Rabbat and R. D. Nowak, “Decentralized source localization and tracking [wireless sensor networks],” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 3, Montreal, Canada, 2004, pp. 921–924.
  17. M. Rabbat, R. Nowak, and J. Bucklew, “Robust decentralized source localization via averaging,” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 5, Philadelphia, PA, 2005, pp. 1057–1060.
  18. P. Hu, V. Bordignon, M. Kayaalp, and A. H. Sayed, “Non-asymptotic performance of social machine learning under limited data,” arXiv:2306.09397, 2023.
  19. V. Bordignon, V. Matta, and A. H. Sayed, “Social learning with partial information sharing,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 5540–5544.
  20. V. Shumovskaia, M. Kayaalp, M. Cemri, and A. H. Sayed, “Discovering influencers in opinion formation over social graphs,” IEEE Open Journal of Signal Processing, vol. 4, pp. 188–207, 2023.
  21. V. Shumovskaia, M. Kayaalp, and A. H. Sayed, “Distributed decision-making for community structured networks,” Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5, April 2024.
  22. ——, “Social learning in community structured graphs,” arXiv:2312.12186, 2023.
  23. A. Mitra, J. A. Richards, and S. Sundaram, “A new approach for distributed hypothesis testing with extensions to byzantine-resilience,” in American Control Conference (ACC), Philadelphia, PA, 2019, pp. 261–266.
  24. L. Su and N. H. Vaidya, “Defending non-bayesian learning against adversarial attacks,” Distributed Computing, vol. 32, pp. 277–289, 2019.
  25. H. Zhang, Y. Li, Y. Hu, Y. Chen, and H. V. Zhao, “Measuring the hazard of malicious nodes in information diffusion over social networks,” in Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2019, pp. 476–481.
  26. H. Zhang, Y. Li, Y. Chen, and H. V. Zhao, “Smart evolution for information diffusion over social networks,” IEEE Transactions on Information Forensics and Security, vol. 16, pp. 1203–1217, 2021.
  27. V. Krishnamurthy and W. Hoiles, “Afriat’s test for detecting malicious agents,” IEEE Signal Processing Letters, vol. 19, no. 12, pp. 801–804, 2012.
  28. C. Zhao, J. He, and J. Chen, “Resilient consensus with mobile detectors against malicious attacks,” IEEE Transactions on Signal and Information Processing over Networks, vol. 4, no. 1, pp. 60–69, 2018.
  29. V. P. Illiano and E. C. Lupu, “Detecting malicious data injections in wireless sensor networks: A survey,” ACM Computing Surveys (CSUR), vol. 48, no. 2, pp. 1–33, 2015.
  30. T. Pang, C. Du, Y. Dong, and J. Zhu, “Towards robust detection of adversarial examples,” Advances in Neural Information Processing Systems, vol. 31, 2018.
  31. H. Zhang, M. A. Alim, X. Li, M. T. Thai, and H. T. Nguyen, “Misinformation in online social networks: Detect them all with a limited budget,” ACM Transactions on Information Systems (TOIS), vol. 34, no. 3, pp. 1–24, 2016.
  32. S. T. Smith, E. K. Kao, E. D. Mackin, D. C. Shah, O. Simek, and D. B. Rubin, “Automatic detection of influential actors in disinformation networks,” Proc. National Academy of Sciences, vol. 118, no. 4, p. e2011216118, 2021.
  33. M. Egele, G. Stringhini, C. Kruegel, and G. Vigna, “Compa: Detecting compromised accounts on social networks.” in NDSS, vol. 13, 2013, pp. 83–91.
  34. M. Tomaiuolo, G. Lombardo, M. Mordonini, S. Cagnoni, and A. Poggi, “A survey on troll detection,” Future Internet, vol. 12, no. 2, p. 31, 2020.
  35. P. Fornacciari, M. Mordonini, A. Poggi, L. Sani, and M. Tomaiuolo, “A holistic system for troll detection on Twitter,” Computers in Human Behavior, vol. 89, pp. 258–268, 2018.
  36. S. Sadiq, A. Mehmood, S. Ullah, M. Ahmad, G. S. Choi, and B.-W. On, “Aggression detection through deep neural model on Twitter,” Future Generation Computer Systems, vol. 114, pp. 120–129, 2021.
  37. L. Xing, K. Deng, H. Wu, P. Xie, H. V. Zhao, and F. Gao, “A survey of across social networks user identification,” IEEE Access, vol. 7, pp. 137 472–137 488, 2019.
  38. B. Qiu, Y. Li, Y. Chen, and H. V. Zhao, “Controlling information diffusion with irrational users,” in Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2019, pp. 482–485.
  39. A. H. Sayed, “Adaptation, learning, and optimization over networks,” Foundations and Trends® in Machine Learning, vol. 7, no. 4-5, pp. 311–801, 2014. [Online]. Available: http://dx.doi.org/10.1561/2200000051
  40. V. Shumovskaia, K. Ntemos, S. Vlaski, and A. H. Sayed, “Explainability and graph learning from social interactions,” IEEE Transactions on Signal and Information Processing over Networks, vol. 8, pp. 946–959, 2022.
  41. A. Kanezaki, Y. Matsushita, and Y. Nishida, “Rotationnet: Joint object categorization and pose estimation using multiviews from unsupervised viewpoints,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 5010–5019.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets