Multitouch Gesture-Based Authentication

Sae-Bae, Napa; Memon, Nasir; Isbister, Katherine; Ahmed, Kowsar

doi:10.1109/tifs.2014.2302582

Cited by 91 publications

(40 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, they employed particle swarm optimization (PSO) to optimize the neural network and reported an improved EER of 2.92%. Authors in [36] acquired 22 multitouch gestures such as drag, swipe, pinch and user-defined gestures on an iPad. They employed dynamic time warping (DTW) for matching and achieved an average EER of 7.88%.…”

Section: Related Work and Motivationmentioning

confidence: 99%

“…8. ROCs for score-level combination of gestures with tanh-estimator for score normalization As a comparative study, we have also implemented dynamic time warping (DTW) based matching, as it has been found very effective [31,34,36] for user authentication based on touchscreen gestures. In order to compare the performance of the proposed approach with DTW, we performed two sets of experiments in the verification mode.…”

Section: A C C E P T E D Mmentioning

confidence: 99%

See 1 more Smart Citation

Exploring orientation and accelerometer sensor data for personal authentication in smartphones using touchscreen gestures

Jain

Kanhangad

2015

Pattern Recognition Letters

View full text Add to dashboard Cite

Section: Related Work and Motivationmentioning

confidence: 99%

Section: A C C E P T E D Mmentioning

confidence: 99%

Exploring orientation and accelerometer sensor data for personal authentication in smartphones using touchscreen gestures

Jain

Kanhangad

2015

Pattern Recognition Letters

View full text Add to dashboard Cite

“…al. [18] dealt with multi touch gestures, especially hand and finger muscle behavior. They pointed the initial points of the five fingers, traced the movement as the fingers move, calculated the distances to propose a gesture based user authentication system and reached 5.14% -27.73% EER.…”

Section: Fig1 Workflow Of Enhanced Swiping Authentication Systemmentioning

confidence: 99%

Biometric Swiping on Touchscreens

Alpar

Krejcar

2015

Computer Information Systems and Industrial Management

View full text Add to dashboard Cite

Abstract. Touchscreen devices have become very popular in the last decade and eased our modern life. It is now possible to automatically log in to any web page connected to our touchscreen phones, such as social networks, e-commerce sites and even mobile banking. Given these facts, the emerging touchscreen technology brings out a potential security issue: weakness of authentication protocols. Therefore, we put forward a biometric enhancement on "swiping" authentication, which is one of the options to log in a touchscreen phone however with the lowest security. We created a ghost password by extracting the features of coordinates and swipe durations to use them as the inputs of the LevenbergMarquardt based neural network and adaptive neuro-fuzzy classifiers which both discriminate real attempts from fraud attacks after training.

show abstract

“…Their classifier achieves a median equal error rate of 0% for intrasession authentication, 2%-3% for intersession authentication, and below 4% when the authentication test was carried out one week after the enrollment phase. Several other related work can be referred to [13,18,19,25]. …”

Section: Related Workmentioning

confidence: 99%

Charging Me and I Know Your Secrets!

Meng

Lee

Murali

et al. 2015

Proceedings of the 1st ACM Workshop on Cyber-Physical System Security

View full text Add to dashboard Cite

Smartphones such as Android phones and iPhones are widely adopted worldwide and the number of smartphone users has increased dramatically. With the popularity of smartphones, the privacy of smartphone users are challenged by various malware and attacks. A large amount of malware has been developed and spread such as Soundcomber, Screenmilker, TouchLogger, and so on. In addition, some smartphone attacks are based on physical access to the phone like smudge attacks. All these have reminded current users to pay more attention for smartphone security such as installing anti-malware software to defend against malicious apps, which may reduce the effectiveness of most malware.In this paper, we identify a vulnerability of smartphone charging and design a new type of charging attacks (called juice filming attacks) based on a standard USB connector and HDMI, which can steal users' secrets through automatically video-capturing their inputs (e.g., unlock patterns, PIN code). The efficiency of our designed attacks relies on the observations that users are not aware of any risk when charging their phones in public places and that most users would interact with their phone during the charging. Different from other malware and attacks, our designed juice filming attacks possess six major features: 1) be simple but quite efficient; 2) user unawareness; 3) does not need to install any apps on phone's side; 4) does not need to ask for any permissions; 5) cannot be detected by any current antimalware software; 6) can be scalable and effective in both Android OS and iOS. To implement this attack, we employ a VGA /RGB frame grabber and further conduct several user studies to explore the feasibility and effectiveness of our attacks. Based on the understanding, we later propose several mitigation strategies to defend against such attacks.

show abstract

Multitouch Gesture-Based Authentication

Cited by 91 publications

References 35 publications

Exploring orientation and accelerometer sensor data for personal authentication in smartphones using touchscreen gestures

Exploring orientation and accelerometer sensor data for personal authentication in smartphones using touchscreen gestures

Biometric Swiping on Touchscreens

Charging Me and I Know Your Secrets!

Contact Info

Product

Resources

About