Deep learning enabled keystroke eavesdropping attack over videoconferencing platforms

Wang, Xueyi, Liu, Yifan and Li, Shancang 2023. Deep learning enabled keystroke eavesdropping attack over videoconferencing platforms. Presented at: IEEE INFOCOM 2023, New York, USA, 20 May 2023. IEEE INFOCOM 2023 - IEEE Conference on Computer Communications Workshops. INFOCOM WKSHPS Hoboken, NJ: IEEE, pp. 1-2. 10.1109/INFOCOMWKSHPS57453.2023.10225861 Item availability restricted.

PDF - Accepted Post-Print Version Restricted to Repository staff only until 23 August 2024 due to copyright restrictions. Download (328kB)

Abstract

The COVID-19 pandemic has significantly impacted people by driving people to work from home using communication tools such as Zoom, Teams, Slack, etc. The users of these communication services have exponentially increased in the past two years, e.g., Teams annual users reached 270 million in 2022 and Zoom averaged 300 million daily active users in videoconferencing platforms. However, using edging artificial intelligence techniques, new cyber attacking tools expose these services to eavesdropping or disruption. This work investigates keystroke eavesdropping attacks on physical keyboards using deep learning techniques to analyze the acoustic emanation of keystroke audios to identify victims' keystrokes. An accurate context-free inferring algorithm was developed that can automatically predict keystrokes during inputs. The experimental results demonstrated that the accuracy of keystroke inference approaches is around 90% over normal laptop keyboards.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	IEEE
Date of First Compliant Deposit:	7 September 2023
Date of Acceptance:	20 May 2023
Last Modified:	11 Sep 2023 15:16
URI:	https://orca.cardiff.ac.uk/id/eprint/162297

Actions (repository staff only)

Edit Item