HIAWare: Speculate Handwriting on Mobile Devices with Built-In Sensors

Chen, Jing; Jiang, Peidong; He, Kun; Zeng, Cheng; Du, Ruxu

doi:10.1007/978-3-030-86890-1_8

Cited by 1 publication

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, we evaluated the TPR of guessing n times in the 3-fold cross-validation, and the result is shown in Figure 9 . Although our experimental speculation space is twice that of J. Chen et al ( Chen et al, 2021a ), our TPR is better than theirs within two guesses. The performance degradation of one guess is only 73.2%, maybe caused by too similar capitalization of some characters, such as ( O , o ), ( S , s ), and ( Z , z ).…”

Section: Experiments Evaluationcontrasting

confidence: 63%

“…From Figure 8 , we can observe that sitting data have the higher speculation accuracy, which can reach 96.1%, and the speculation accuracy of standing data is 91.1%, which are both better than the experimental results (93.5% for sitting, 81.4% for standing) of J. Chen et al ( Chen et al, 2021a ). The experimental performance in the sitting posture is better than that in the standing posture, because the sitting posture has less background noise, and we can extract more handwriting segments from the collected sensors’ signals to fully train the speculation model.…”

Section: Experiments Evaluationmentioning

confidence: 63%

“…Spider-inspired HCCapture is an improvement of J. Chen et al’s work ( Chen et al, 2021a ). Compared to the previous version, we have made three major improvements.…”

Section: Introductionmentioning

confidence: 95%

“…In this article, we quoted the modified constant false alarm rate (mCFAR) algorithm proposed by J. Chen et al ( Chen et al, 2021a ), to identify handwriting actions from the motion sensors’ signals. The mathematical description of our algorithm is shown as Algorithm 1 .…”

Section: Implementsmentioning

confidence: 99%

See 3 more Smart Citations

Spider-Inspired HCCapture: Beware That What You Are Writing on Mobile Devices Is Becoming Prey for Spiders

Zhu

Chen

et al. 2022

Front. Bioeng. Biotechnol.

Self Cite

View full text Add to dashboard Cite

On mobile devices, the most important input interface is touchscreen, which can transmit a large amount of sensitive information. Many researchers have proven that sensors can be used as side channels to leak touchscreen interactive information. The research of information leakage in the restricted area has been relatively mature, but in the unrestricted area, still there are two issues to be solved urgently: chirography difference and posture variation. We learn from the way spiders perceive prey through the subtle vibrations of their webs; an unrestricted-area handwriting information speculation framework, called spider-inspired handwriting character capture (spider-inspired HCCapture), is designed. Spider-inspired HCCapture exploits the motion sensor as the side-channel and uses the neural network algorithm to train the recognition model. To alleviate the impact of different handwriting habits, we utilize the generality patterns of characters rather than the patterns of raw sensor signals. Furthermore, each character is disassembled into basic strokes, which are used as recognition features. We also proposed a user-independent posture-aware approach to detect the user’s handwriting posture to select a suitable one from some pretrained models for speculation. In addition, the Markov model is introduced into spider-inspired HCCapture, which is used as an enhancement feature when there is a correlation between adjacent characters. In conclusion, spider-inspired HCCapture completes the handwritten character speculation attack without obtaining the victim’s information in advance. The experimental results show that the accuracy of spider-inspired HCCapture reaches 96.1%.

show abstract

Section: Experiments Evaluationcontrasting

confidence: 63%

Section: Experiments Evaluationmentioning

confidence: 63%

“…Spider-inspired HCCapture is an improvement of J. Chen et al’s work ( Chen et al, 2021a ). Compared to the previous version, we have made three major improvements.…”

Section: Introductionmentioning

confidence: 95%

Section: Implementsmentioning

confidence: 99%

See 2 more Smart Citations