Abstract
Semi-supervised learning plays an important role in pattern classification as it learns from not only the labeled sample but also the unlabeled samples. It saves the cost and time on sample labeling. Recently, semi-supervised learning has been applied in many security applications. An adversary may present in these applications to confuse the learning processes. In this paper, we investigate the influence of the adversarial attack on the semi-supervised learning. We propose a causative attack, which injects the attack samples in the training set, to mislead the training of the semi-supervised learning. The experimental results show the accuracy of the classifier trained by the semi-supervised learning drop significantly after attacking by our proposed model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Mitchell, T.M., Zeng, J.-H. (trans.): Machine Learning, pp. 2–5. China Machine Press (2003)
Mohri, M., Rostamizadeh, A., Talwalkar, A.: Foundations of Machine Learning, pp. 1–14. MIT Press (2012)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, pp. 517–518 . Wiley-InterScience (2000)
Zhu, X.-J., Goldberg, A.B.: Introduction to Semi-Supervised Learning, pp. 1–130. Morgan & Claypool Publishers (2009)
Chapelle, O., Sch¨olkopf, B., Zien, A.: Semi-Supervised Learning, pp. 119–134. MIT Press (2006)
Zhou, Y., Jorgensen, Z., Inge, M.: Combating Good Word Attacks on Statistical Spam Filters with Multiple Instance Learning. In: ICTAI, pp. 298–305 (2007)
Wang, X.-W., Wang, Z.-F.: Good Word Attack Spam Filtering Model Based On Artificial Immune System. In: ACAI, pp. 1106–1109 (2012)
Zhu, F., Long, J., Zhao, W., Cai, Z.: A Misleading Attack against Semi-supervised Learning for Intrusion Detection. In: Torra, V., Narukawa, Y., Daumas, M. (eds.) MDAI 2010. LNCS, vol. 6408, pp. 287–298. Springer, Heidelberg (2010)
Nelson, B.: Behavior of Machine Learning Algorithms in Adversarial Environments, Phd Dissertation, pp. 37–55 (2010)
Lowd, D., Meek, C.: Adversarial Learning. ACM SIGKDD, pp. 641–647 (2005)
Nelson, B., Biggio, B., Laskov, P.: Understanding the Risk Factors of Learning in Adversarial Environments. In: ACM Workshop on Artificial Intelligence and Security, pp. 87–92 (2011)
Newsome, J., Karp, B., Song, D.: Poly graph: Automatically generating signatures for polymorphic worms. In: S&P IEEE Symposium, pp. 226–241 (2005)
Zhou, X.-C., Shen, H.-B., Huang, Z.-Y., Li, G.-J.: Large margin classification for combating disguise attacks on spam filters. Journal of Zhejiang University SCIENCE C, 155–238 (2012)
Luo, R.C., Lin, P.-H., Wu, Y.-C., Huang, C.-Y.: Dynamic face recognition system in recognizing facial expressions for service robotics. In: AIM, pp. 879–884 (2012)
Joachims, T.: Transductive Inference for Text Classification using Support Vector Machines. In: ICML, pp. 200–209 (1999)
Zhou, Z.-H.: Co-Training with Insufficient Views. In: ACML, pp. 467–482 (2013)
Ushakov, N.G.: Density of a probability distribution, Encyclopedia of Mathematics, pp. 313–333. Springer (2001)
Gut, A.: Probability: A Graduate Course, pp. 113–122. Springer (2005)
Bishop, C.M., Lasserre, J.: Generative or Discriminative? getting the best of both worlds. Bayesian Statistics 8, 3–23 (2007)
Mao, C.H., Lee, H.M., Parikh, D., Chen, T., Huang, S.Y.: Semi-supervised co-training and active learning based approach for multi-view intrusion detection. In: ACM SAC, pp. 2042–2048 (2009)
Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT, pp. 92–100 (1998)
Zhou, Z.-H., Li, M.: Semi-Supervised Regression with Co-Training. In: IJCAI, pp. 1479–1493 (2007)
Qin, Z.-C.: Naive Bayes Classification Given Probability Estimation Trees. In: ICMLA, pp. 34–42 (2006)
Archive, T.U.K.: Kdd cup 1999 data (1999)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, Y., Yeung, D.S. (2014). A Causative Attack Against Semi-supervised Learning. In: Wang, X., Pedrycz, W., Chan, P., He, Q. (eds) Machine Learning and Cybernetics. ICMLC 2014. Communications in Computer and Information Science, vol 481. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45652-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-662-45652-1_21
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45651-4
Online ISBN: 978-3-662-45652-1
eBook Packages: Computer ScienceComputer Science (R0)