Cryptographic Limitations on Polynomial-Time a Posteriori Query Learning

  • Mikito NanashimaEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10979)


We investigate the polynomial-time learnability by using examples and membership queries. Angluin and Kharitonov [1] proved that various concept classes (e.g., Boolean formulae, non-deterministic finite automata) are not polynomial-time learnable in this learning model based on a public-key encryption scheme with a certain security (i.e., IND-CCA1). As a stronger learning model, we consider an a posteriori query learning model, and show that it is indeed stronger than the above learning model if a one-way function exists. Nevertheless, from a secure encryption scheme, we prove that many natural classes containing Boolean formula concept class is not polynomial-time learnable even in this stronger learning model. The security of an encryption scheme used in this paper is weaker than the one used by Angluin and Kharitonov.


Computational learning theory PAC learning Query learning Cryptography Encryption Signature 


  1. 1.
    Angluin, D., Kharitonov, M.: When won’t membership queries help? J. Comput. Syst. Sci. 50(2), 336–355 (1995)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Goldreich, O.: Foundations of Cryptography: Volume 2, Basic Applications. Cambridge University Press, New York (2004)CrossRefGoogle Scholar
  3. 3.
    Goldwasser, S., Micali, S., Rivest, R.L.: A digital signature scheme secure against adaptive chosen-message attacks. SIAM J. Comput. 17(2), 281–308 (1988)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Haussler, D., Kearns, M., Littlestone, N., Warmuth, M.K.: Equivalence of models for polynomial learnability. In: Proceedings of the First Annual Workshop on Computational Learning Theory, pp. 42–55 (1988)Google Scholar
  5. 5.
    Impagliazzo, R., Luby, M.: One-way functions are essential for complexity based cryptography. In: Proceedings of the 30th Annual Symposium on Foundations of Computer Science, pp. 230–235 (1989)Google Scholar
  6. 6.
    Pitt, L., Warmuth, M.K.: Prediction-preserving reducibility. J. Comput. Syst. Sci. 41(3), 430–467 (1990)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Rompel, J.: One-way functions are necessary and sufficient for secure signatures. In: Proceedings of the Twenty-Second Annual ACM Symposium on Theory of Computing, pp. 387–394 (1990)Google Scholar
  8. 8.
    Schapire, R.E.: The strength of weak learnability. Mach. Learn. 5(2), 197–227 (1990)Google Scholar
  9. 9.
    Stern, J., Pointcheval, D., Malone-Lee, J., Smart, N.P.: Flaws in applying proof methodologies to signature schemes. In: Yung, M. (ed.) CRYPTO 2002. LNCS, vol. 2442, pp. 93–110. Springer, Heidelberg (2002). Scholar
  10. 10.
    Valiant, L.G.: A theory of the learnable. Commun. ACM 27(11), 1134–1142 (1984)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Mathematical and Computing ScienceTokyo Institute of TechnologyTokyoJapan

Personalised recommendations