History

Keyboard Acoustic Emanations Revisited

ACM Transactions on Information and System Security 2009, University of California, Berkeley.

Abstract: We present a novel attack taking as input a 10-minute sound recording of a user typing English text using a keyboard and recovering up to 96% of typed characters. There is no need for training recordings labeled with the corresponding clear text. A recognizer bootstrapped from a 10-minute sound recording 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 by an adversary. In the attack, we use the statistical constraints of the underlying content, English language, to reconstruct text from sound recordings without knowing the corresponding clear text. The attack incorporates a combination of standard machine learning and speech recognition techniques, including cepstrum features, Hidden Markov Models, linear classification, and feedback-based incremental learning

  • with training data: apply several acoustic processing then machine learning
  • without training data: feature extraction -> clustering -> language model
  • Keystroke Recognition Using WiFi Signals

    ACM MobiCom 2015, Michigan State University & Nanjing University

    ...In this paper, we show for the first time that WiFi signals can also be exploited to recognize keystrokes. The intuition is that while typing a certain key, the hands and fingers of a user move in a unique formation and direction and thus generate a unique pattern in the time-series of Channel State Information (CSI) values, which we call CSI-waveform for that key.

    Overview

    When CSI Meets Public WiFi: Inferring Your Mobile Phone Password via WiFi Signals

    ACM SIGSAC Conference on Computer and Communications Security 2016, Shanghai Jiao Tong University & University of Massachusetts at Boston & University of South Florida

    ...WindTalker is motivated from the observation that keystrokes on mobile devices will lead to different hand coverage and the finger motions, which will introduce a unique interference to the multi-path signals and can be reflected by the channel state information (CSI). WindTalker presents a novel approach to collect the target's CSI data by deploying a public WiFi hotspot.

    Details

    Data collection

  • start eavesdropping only when user use HTTPS
  • use a Sensitive IP Pool to recognize AliPay or similar apps
  • use ICMP to force transmission to collect CSI data (800 packets/s)
  • Data Processing

  • Low pass filter
  • PCA
  • Keystroke Inference

    Result

    successfully recover 2, 4, 7 and 9 passwords if allowing to try the password input for 5, 10, 50 and 100 times (or Top 5, 10, 50, and 100 candidates).

    Advantages

  • Do not require an external device close to the target
  • Do not compromise target device
  • Hard to detect since it's just a normal public WiFi
  • Can be used together with traffic information
  • Disadvantages

  • Require a device and driver that provides open access to CSI value.
  • Need training data of the same configuration (device, environment, gesture, etc.). A possible solution is to use captcha to have user type specific text.
  • Following works

  • motion and gesture recognition
  • train more robust model that handle different configuration.