Abstract
This paper suggests a novel verification system for handwritten signatures. The proposed system is based on capturing motion signals from the sensors of wrist-worn devices, such as smartwatches and fitness trackers, during the signing process, to train a machine learning classifier to determine whether a given signature is genuine or forged. Our system can be used to: (1) Verify signatures written on paper documents, such as checks, credit card receipts and vote by mail ballots. Unlike existing systems for signature verification, our system obtains a high degree of accuracy, without requiring an ad hoc digital signing device. (2) Authenticate a user of a secure system based on "who you are" traits. Unlike existing "motion-based" authentication methods that commonly rely on long-term user behavior, writing a signature is a relatively short-term process. In order to evaluate our system, we collected 1,980 genuine and forged signature recordings from 66 different subjects, captured using a smartwatch device. Applying our signature verification system on the collected dataset, we show that it significantly outperforms two other state-of-the-art systems, obtaining an EER of 2.36% and an AUC of 98.52%.
- Hervé Abdi and Lynne J Williams. 2010. TukeyâĂźs honestly significant difference (HSD) test. Encyclopedia of Research Design. Thousand Oaks, CA: Sage (2010), 1--5.Google Scholar
- Luca Ardüser, Pascal Bissig, Philipp Brandes, and Roger Wattenhofer. {n. d.}. Recognizing Text Using Motion Data From a Smartwatch. ({n. d.}).Google Scholar
- Gonzalo Bailador, Carmen Sanchez-Avila, Javier Guerra-Casanova, and Alberto de Santos Sierra. 2011. Analysis of pattern recognition techniques for in-air signature biometrics. Pattern Recognition 44, 10 (2011), 2468--2478. Google ScholarDigital Library
- Tony Beltramelli and Sebastian Risi. 2015. Deep-Spying: Spying using Smartwatch and Deep Learning. arXiv preprint arXiv:1512.05616 (2015).Google Scholar
- A blog-to watch. 2015. (2015). http://www.ablogtowatch.com/poll-your-hand-orientation-what-wrist-wear-your-watch/ Accessed: 2017-11-01.Google Scholar
- David Bolton. {n. d.}. Ditching smartphones for wearables. http://arc.applause.com/2015/10/15/wearables-apple-watch-fitness-tracker/. ({n. d.}). Accessed: 2016-03-18.Google Scholar
- Christopher Carlson, Toney Chen, Jeremy Cruz, Javid Maghsoudi, Hui Zhao, and John V Monaco. 2015. User Authentication with Android Accelerometer and Gyroscope Sensors. Proceedings of Student-Faculty Research Day, CSIS, Pace University (2015).Google Scholar
- J Guerra Casanova, C Sánchez Ávila, Alberto de Santos Sierra, G Bailador del Pozo, and V Jara Vera. 2010. A real-time in-air signature biometric technique using a mobile device embedding an accelerometer. In International Conference on Networked Digital Technologies. Springer, 497--503.Google ScholarCross Ref
- N. L. Clarke and S. M. Furnell. 2007. Authenticating mobile phone users using keystroke analysis. International Journal of Information Security 6, 1 (2007), 1--14. Google ScholarDigital Library
- Scott Davidson, Derrick Smith, Chen Yang, and Sebastian Cheah. 2016. Smartwatch User Identification as a Means of Authentication. Department of Computer Science and Engineering Std (2016).Google Scholar
- Julian Fierrez, Javier Ortega-Garcia, Daniel Ramos, and Joaquin Gonzalez-Rodriguez. 2007. HMM-based online signature verification: Feature extraction and signature modeling. Pattern recognition letters 28, 16 (2007), 2325--2334. Google ScholarDigital Library
- Andreas Fischer, Moises Diaz, Rejean Plamondon, and Miguel A Ferrer. 2015. Robust score normalization for DTW-based online signature verification. In Document Analysis and Recognition (ICDAR), 2015 13th International Conference on. IEEE, 241--245. Google ScholarDigital Library
- 2015 AFP Payments Fraud and Control Survey. 2015. (2015). https://nacm.org/pdfs/surveyResults/afp-payments-fraud-results.pdf Accessed: 2016-09-30.Google Scholar
- Marta Gomez-Barrero, Julian Fierrez, and Javier Galbally. 2016. Variable-length template protection based on homomorphic encryption with application to signature biometrics. In 2016 4th International Conference on Biometrics and Forensics (IWBF). IEEE, 1--6.Google ScholarCross Ref
- Javier Guerra-Casanova, Carmen Sánchez Ávila, Gonzalo Bailador, and Alberto de Santos-Sierra. 2011. Time series distances measures to analyze in-air signatures to authenticate users on mobile phones. In Security Technology (ICCST), 2011 IEEE International Carnahan Conference on. IEEE, 1--7.Google ScholarCross Ref
- Jeremy Gummeson, Bodhi Priyantha, and Jie Liu. 2014. An energy harvesting wearable ring platform for gestureinput on surfaces. In Proceedings of the 12th annual international conference on Mobile systems, applications, and services. ACM, 162--175. Google ScholarDigital Library
- Luiz G Hafemann, Robert Sabourin, and Luiz S Oliveira. 2015. Offline Handwritten Signature Verification-Literature Review. arXiv preprint arXiv:1507.07909 (2015).Google Scholar
- Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H Witten. 2009. The WEKA data mining software: an update. ACM SIGKDD explorations newsletter 11, 1 (2009), 10--18. Google ScholarDigital Library
- Donato Impedovo and Giuseppe Pirlo. 2008. Automatic signature verification: the state of the art. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on 38, 5 (2008), 609--635. Google ScholarDigital Library
- Vahab Iranmanesh, Sharifah Mumtazah Syed Ahmad, Wan Azizun Wan Adnan, Salman Yussof, Olasimbo Ayodeji Arigbabu, and Fahad Layth Malallah. 2014. Online handwritten signature verification using neural network classifier based on principal component analysis. The Scientific World Journal 2014 (2014).Google Scholar
- Felix Juefei-Xu, Chandrasekhar Bhagavatula, Aaron Jaech, Unni Prasad, and Marios Savvides. 2012. Gait-id on the move: Pace independent human identification using cell phone accelerometer dynamics. In Biometrics: Theory, Applications and Systems (BTAS), 2012 IEEE Fifth International Conference on. IEEE, 8--15.Google ScholarCross Ref
- Alisher Kholmatov and Berrin Yanikoglu. 2005. Identity authentication using improved online signature verification method. Pattern recognition letters 26, 15 (2005), 2400--2408. Google ScholarDigital Library
- Rajesh Kumar, Vir V Phoha, and Rahul Raina. 2016. Authenticating users through their arm movement patterns. arXiv preprint arXiv:1603.02211 (2016).Google Scholar
- A. Lewis, Y. Li, and M. Xie. 2016. Real time motion-based authentication for smartwatch. In 2016 IEEE Conference on Communications and Network Security (CNS). 380--381.Google Scholar
- Lingjun Li, Xinxin Zhao, and Guoliang Xue. 2013. Unobservable Re-authentication for Smartphones.. In NDSS.Google Scholar
- Muhammad Imran Malik and Marcus Liwicki. 2012. From terminology to evaluation: Performance assessment of automatic signature verification systems. In Frontiers in Handwriting Recognition (ICFHR), 2012 International Conference on. IEEE, 613--618. Google ScholarDigital Library
- Jani Mantyjarvi, Mikko Lindholm, Elena Vildjiounaite, S-M Makela, and HA Ailisto. 2005. Identifying users of portable devices from gait pattern with accelerometers. In Acoustics, Speech, and Signal Processing, 2005. Proceedings.(ICASSP'05). IEEE International Conference on, Vol. 2. IEEE, ii--973.Google Scholar
- The 10 most likely sensors in a 10-sensor Apple smartwatch. 2014. (2014). https://www.pcworld.com/article/2366126/the-10-most-likely-sensors-in-a-10-sensor-apple-smartwatch.html Accessed: 2016-09-30.Google Scholar
- Myo. 2016. (2016). https://www.myo.com/ Accessed: 2016-09-30.Google Scholar
- Mohammad Reza Nilchiyan and Rubiyah Bte Yusof. 2013. Improved wavelet-based online signature verification scheme considering pen scenario information. In Artificial Intelligence, Modelling and Simulation (AIMS), 2013 1st International Conference on. IEEE, 8--13. Google ScholarDigital Library
- Shahriar Nirjon, Robert Dickerson, John Stankovic, Guobin Shen, and Xiaofan Jiang. 2013. sMFCC: exploiting sparseness in speech for fast acoustic feature extraction on mobile devices--a feasibility study. In Proceedings of the 14th Workshop on Mobile Computing Systems and Applications. ACM, 8. Google ScholarDigital Library
- Sampo Ojala, Jari Keinanen, and Jorma Skytta. 2008. Wearable authentication device for transparent login in nomadic applications environment. In Signals, Circuits and Systems, 2008. SCS 2008. 2nd International Conference on. IEEE, 1--6.Google Scholar
- Vishal M Patel, Rama Chellappa, Deepak Chandra, and Brandon Barbello. 2016. Continuous user authentication on mobile devices: Recent progress and remaining challenges. IEEE Signal Processing Magazine 33, 4 (2016), 49--61.Google ScholarCross Ref
- Rejean Plamondon and Guy Lorette. 1989. Automatic signature verification and writer identification?the state of the art. Pattern recognition 22, 2 (1989), 107--131.Google Scholar
- Réjean Plamondon and Sargur N Srihari. 2000. Online and offline handwriting recognition: a comprehensive survey. Pattern Analysis and Machine Intelligence, IEEE Transactions on 22, 1 (2000), 63--84. Google ScholarDigital Library
- Juhi Ranjan and Kamin Whitehouse. 2015. Object hallmarks: Identifying object users using wearable wrist sensors. In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. ACM, 51--61. Google ScholarDigital Library
- K Ramamohan Rao and Ping Yip. 2014. Discrete cosine transform: algorithms, advantages, applications. Academic press. Google ScholarDigital Library
- Saeid Rashidi, Ali Fallah, and Farzad Towhidkhah. 2012. Authentication based on signature verification using position, velocity, acceleration and Jerk signals. In Information Security and Cryptology (ISCISC), 2012 9th International ISC Conference on. IEEE, 26--31.Google ScholarCross Ref
- S Rashidi, A Fallah, and F Towhidkhah. 2012. Feature extraction based DCT on dynamic signature verification. Scientia Iranica 19, 6 (2012), 1810--1819.Google ScholarCross Ref
- Napa Sae-Bae and Nasir Memon. 2013. A simple and effective method for online signature verification. In Biometrics Special Interest Group (BIOSIG), 2013 International Conference of the. IEEE, 1--12.Google Scholar
- Abdul Serwadda, Vir V. Phoha, and Zibo Wang. 2013. Which verifiers work?: A benchmark evaluation of touch-based authentication algorithms. IEEE Computer Society.Google Scholar
- Ho-chul Shin. 2016. WEARABLE DEVICE AND METHOD OF OPERATING THE SAME. (Feb. 4 2016). US Patent 20,160,034,041.Google Scholar
- 2013 ABA Deposit Account Fraud Survey. 2013. (2013). http://www.aba.com/Products/Surveys/Pages/2013DepositAccount.aspxAccessed: 2016-09-30.Google Scholar
- Rozita Teymourzadeh, Waidhuba Martin Kizito, Kok Wai Chan, and Mok Vee Hoong. 2013. Smart analytical signature verification for DSP applications. In Systems, Process 8 Control (ICSPC), 2013 IEEE Conference on. IEEE, 301--305.Google Scholar
- USAtoday. 2017. (2017). http://www.cbsnews.com/news/florida-voters-can-fix-vote-by-mail-ballot-federal-judge-rules/ Accessed: 2017-11-01.Google Scholar
- He Wang, Ted Tsung-Te Lai, and Romit Roy Choudhury. 2015. Mole: Motion leaks through smartwatch sensors. In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking. ACM, 155--166. Google ScholarDigital Library
- Wikipedia. {n. d.}. Discrete cosine transform. ({n. d.}). https://en.wikipedia.org/wiki/Discretecosinetransform.Google Scholar
- Chao Xu, Parth H Pathak, and Prasant Mohapatra. 2015. Finger-writing with smartwatch: A case for finger and hand gesture recognition using smartwatch. In Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications. ACM, 9--14. Google ScholarDigital Library
- Berrin Yanikoglu and Alisher Kholmatov. 2009. Online signature verification using fourier descriptors. EURASIP Journal on Advances in Signal Processing 2009 (2009), 12. Google ScholarDigital Library
- Dit-Yan Yeung, Hong Chang, Yimin Xiong, Susan George, Ramanujan Kashi, Takashi Matsumoto, and Gerhard Rigoll. 2004. SVC2004: First international signature verification competition. In Biometric Authentication. Springer, 16--22.Google Scholar
- Heng Zhang, Vishal M Patel, Mohammed Fathy, and Rama Chellappa. 2015. Touch gesture-based active user authentication using dictionaries. In Applications of Computer Vision (WACV), 2015 IEEE Winter Conference on. IEEE, 207--214. Google ScholarDigital Library
Index Terms
- Handwritten Signature Verification Using Wrist-Worn Devices
Recommendations
Random forgery attacks against DTW-based online signature verification algorithm
SAC '11: Proceedings of the 2011 ACM Symposium on Applied ComputingSkilled forged signatures are one of the most difficult to distinguish from genuine signatures and randomly forged signatures are considered to be less difficult than skilled forged signatures. However, since the FARs are generally calculated by ...
An efficient online signature verification scheme using dynamic programming of string matching
ICHIT'11: Proceedings of the 5th international conference on Convergence and hybrid information technologyThe necessity to authenticate individuals is rapidly increasing day by day with the explosive growth of E-commerce, E-finance, PDA, etc. Handwritten signature is the most widely used and easiest way to verify a person. Online signature verification is a ...
A Provably Secure Server-Aided Verification Signature
EIDWT '13: Proceedings of the 2013 Fourth International Conference on Emerging Intelligent Data and Web TechnologiesA server-aided verification signature scheme consists of a standard signature scheme and a server-aided verification protocol. Signatures can be verified by executing the server-aided verification protocol with the server, which is generally untrusted. ...
Comments