Keyboard acoustic emanations revisited

By Zhuang Li, Feng Zhou, J. Doug Tygar, Daniel Liu. Conference on Computer and Communications Security, 2005

343 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f077ed62b4de5f4dfa74007bb6a0300b8f31f305

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

(sp)iPhone: decoding vibrations from nearby keyboards using mobile phone accelerometers (2011, background): “[42], the neural network does not have to be retrained in this manner.”
On the (In)effectiveness of Mosaicing and Blurring as Tools for Document Redaction (2016, unknown): “Hidden Markov models of English text have been used in other security research— for example, to recover keystrokes from their acoustic emanations [21], and to recover spoken text from the size of encrypted VoIP packets [20].”
Intel SGX Explained (2016, methodology): “[201] used a directional microphone to measure the sound emitted by a keyboard and learn the password that its operator typed.”
AccelPrint: Imperfections of Accelerometers Make Smartphones Trackable (2014, methodology): “Electromagnetic waves [65], acoustic signals [71], timing events [38], and specialized software [36] were exploited to intercept the keystrokes with high accuracy.”
Security Requirements Engineering: A Framework for Representation and Analysis (2008, background): “We explore these criteria in this section, providing background and motivation for our contributions.”
TouchLogger: Inferring Keystrokes on Touch Screen from Smartphone Motion (2011, background): “Key logging based on side channelsResearchers have studied keystroke inference based on side channels, such as sound [2, 11], electromaganetic wave [8], and timing [7, 4].”
The Plight of the Targeted Attacker in a World of Scale (2010, methodology): “Attacks that seek to spy using reﬂected light, electromagnetic emissions, or sound [29, 31, 34] clearly require proximity and are non-scalable.”
On the Feasibility of Internet-Scale Author Identification (2012, methodology): “identifying the file type of a binary blob [33] and recovering text typed on a keyboard based on acoustic emanations [34] use similar techniques, although the models are simpler than linguistic stylometry.”
ACCessory: password inference using accelerometers on smartphones (2012, unknown): “, based on sound [3, 23] and inter-”
Tapprints: your finger taps have fingerprints (2012, background): “Researchers exploit electromagnetic waves [18], acoustic signals [27], timing events [14], and specialized software [28] to intercept the typed content with high accuracy.”
Edge Computing Security: State of the Art and Challenges (2019, background): “[72] independently showed that it is feasible to infer a user’s keystroke by analyzing the acoustic sounds emitted from the physical keyboards which existed in early-stage smartphones.”
Keystroke Recognition Using WiFi Signals (2015, background): “Acoustic emission based approaches recognize keystrokes based on either the observation that different keys in a keyboard produce different typing sounds [1, 2] or the observation that the acoustic emanations from different keys arrive at different surrounding smartphones at different time as the ke”
Compromising Electromagnetic Emanations of Wired and Wireless Keyboards (2009, positive): “This attack was later improved, see [38, 7].”