Team for Research in
Ubiquitous Secure Technology

Citation
Li Zhuang, Feng Zhou, J. D. Tygar. "Keyboard Acoustic Emanations Revisited". To appear in Proceedings of the 12th ACM Conference on Computer and Communications Security, November 2005.

Abstract
We examine the problem of keyboard acoustic emanations. We present a novel attack taking as input a 10-minute sound recording of a user typing English text using a keyboard, and then recovering up to 96% of typed characters. There is no need for a labeled training recording. Moreover the recognizer bootstrapped this way can even recognize random text such as passwords: In our experiments, 90% of 5-character random passwords using only letters can be generated in fewer than 20 attempts by an adversary; 80% of 10- character passwords can be generated in fewer than 75 attempts. Our attack uses the statistical constraints of the underlying content, English language, to reconstruct text from sound recordings without any labeled training data. The attack uses a combination of standard machine learning and speech recognition techniques, including cepstrum features, Hidden Markov Models, linear classification, and feedback-based incremental learning.

Categories and Subject Descriptors: K.6.5 Security and Protection: Unauthorized access; K.4.1 Public Policy Issues: Privacy General Terms: Security

Keywords: Computer Security, Human Factors, Acoustic Emanations, Learning Theory, Hidden Markov Models, HMM, Cepstrum, Signal Analysis, Keyboards, Privacy, Electronic Eavesdropping

Electronic downloads

• ZhaungZhouTygarKeyboardAcousticEmanationsRevisted.pdf · application/pdf · 350 kbytes. (To appear)

• HTML

  Li Zhuang, Feng Zhou, J. D. Tygar. <a
  href="http://www.truststc.org/pubs/3.html"
  >Keyboard Acoustic Emanations Revisited</a>,
  <i>To appear in Proceedings of the 12th ACM Conference
  on Computer and Communications Security</i>, November
  2005.

• Plain text

  Li Zhuang, Feng Zhou, J. D. Tygar. "Keyboard Acoustic
  Emanations Revisited". <i>To appear in
  Proceedings of the 12th ACM Conference on Computer and
  Communications Security</i>, November 2005.

• BibTeX

  @article{ZhuangZhouTygar05_KeyboardAcousticEmanationsRevisited,
      author = {Li Zhuang, Feng Zhou, J. D. Tygar},
      title = {Keyboard Acoustic Emanations Revisited},
      journal = {To appear in Proceedings of the 12th ACM
                Conference on Computer and Communications Security},
      month = {November},
      year = {2005},
      abstract = {We examine the problem of keyboard acoustic
                emanations. We present a novel attack taking as
                input a 10-minute sound recording of a user typing
                English text using a keyboard, and then recovering
                up to 96% of typed characters. There is no need
                for a labeled training recording. Moreover the
                recognizer bootstrapped this way can even
                recognize random text such as passwords: In our
                experiments, 90% of 5-character random passwords
                using only letters can be generated in fewer than
                20 attempts by an adversary; 80% of 10- character
                passwords can be generated in fewer than 75
                attempts. Our attack uses the statistical
                constraints of the underlying content, English
                language, to reconstruct text from sound
                recordings without any labeled training data. The
                attack uses a combination of standard machine
                learning and speech recognition techniques,
                including cepstrum features, Hidden Markov Models,
                linear classification, and feedback-based
                incremental learning. <p>Categories and Subject
                Descriptors: K.6.5 Security and Protection:
                Unauthorized access; K.4.1 Public Policy Issues:
                Privacy General Terms: Security <p>Keywords:
                Computer Security, Human Factors, Acoustic
                Emanations, Learning Theory, Hidden Markov Models,
                HMM, Cepstrum, Signal Analysis, Keyboards,
                Privacy, Electronic Eavesdropping },
      URL = {http://www.truststc.org/pubs/3.html}
  }
  

Posted by Christopher Brooks on 16 Sep 2005.
Groups: trust
For additional information, see the Publications FAQ or contact webmaster at www truststc org.