Sequential Keystroke Behavioral Biometrics for Mobile User Identification via Multi-view Deep Learning

Sun, Lichao; Wang, Yuqi; Cao, Binggang; Yu, Philip S.; Srisa-an, Witawas; Leow, Alex D.

doi:10.1007/978-3-319-71273-4_19

Cited by 50 publications

(37 citation statements)

References 18 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mengingat maraknya penipuan pada situs e-commerce yang dapat mengakibatkan kerugian finansial yang cukup besar, sebagai konsumen perlu adanya pengetahuan mengenai jenis penipuan yang umum terjadi dan metode pencegahan yang digunakan untuk mendeteksi penipuan agar terhindar dari berbagai kerugian. Beberapa penelitian sebelumnya hanya membahas tentang identifikasi dan metode pencegahan penipuan e-commerce ( Makarti, 2011;Chang & Chang, 2012;Syed & Shabbir, 2013;Valentin, 2013;Caldeira, Brandao, & Pereira, 2014;Leung, Lai, Chen, & Wan, 2014;Massa & Valverde, 2014;Hwang & Lai, 2015;JRana & Baria, 2015;Singh & Singh, 2015;Abdallah, Maarof, & Zainal, 2016;Beránek, Nýdl, & Remeš, 2016;Gerlach, Pavlovic, & Gerlach, 2016;Lima & Pereira, 2016;Yang et al, 2016;Ramadhan & Amelia, 2016;Sun et al, 2017;Prisha, Neo, Ong, & Teo, 2017;Raghava-Raju, 2017;Shaji & Panchal, 2017;Wiralestari, 2017;Renjith, 2018;Weng et al, 2018;Zhao et al, 2018;Zheng et al, 2018); Amasiatu Amiruddin et al, 2019;Carta et al, 2019;Raghavan & Gayar, 2019;Shah et al, 2019;Soomro et al, 2019. Sementara penelitian lainnya lebih fokus pada penipuan sistem pembayaran dan penipuan terkait dengan pelanggan (Keraf & Hidup, 2010;Rofiq & Mula, 2010;Raj & Portia, 2011;Hu, Liu, & Sambamurthy, 2011;…”

Section: Pendahuluanunclassified

Pemetaan Bentuk Dan Pencegahan Penipuan E-Commerce

Dewi

Mahyuni

2020

EEB

View full text Add to dashboard Cite

Seiring berkembangnya transaksi jual beli, penipuan elektronik juga turut meningkat sehingga mengakibatkan banyak konsumen yang telah mengalami kerugian akibat penipuan yang terjadi. Tujuan dari penelitian ini adalah untuk mengetahui jenis penipuan yang dapat terjadi dalam perdagangan elektronik dan pencegahan yang dapat dilakukan. Dalam penelitian ini disajikan review dengan metode pendekatan interpretif atas artikel terkait, dengan proses pemetaan pada artikel yang dikumpulkan melalui situs Google Cendekia, Elsevier, Springer, Taylor & Francis, dan MDPI (Multidisciplinary Digital Publishing Institute). Dari sumber tersebut, 105 artikel berhasil dikumpulkan, setelah proses seleksi artikel berdasarkan 10 tahun terahir dan kesesuaian pembahasan akhirnya diperoleh 55 artikel. Hasil penelitian ini adalah ditemukan berbagai jenis penipuan pada keempat kategori e-coomerce serta penipuan pada sistem pebayaran dan penipuan pada e-commerce yang menyangkut pelanggan. Metode modern pendeteksi penipuan juga disajikan dalam penelitian ini, seperti data mining, jaringan bayesan, algoritma, mesin pendukung vector, pemrograman genetik, pohon pengambilan keputusan, Adaptive Neuro-Fuzzy Inference System, Situs Web Bantuan Perlindungan (PAW), dan Model Privacy Antecedent-Privacy Concern-Outcomes (APCO). Dengan penjabaran pada hasil penelitian ini, konsumen diharapkan untuk lebih berhati-hati saat melakukan transaksi di situs e-commerce agar terhindar dari berbagai tindak penipuan.

show abstract

Section: Pendahuluanunclassified

Pemetaan Bentuk Dan Pencegahan Penipuan E-Commerce

Dewi

Mahyuni

2020

EEB

View full text Add to dashboard Cite

show abstract

“…Other datasets have also been experimented. DeepService [11] focuses on mobile-phone free-text authentication. Using a multi-class (one per user) and multi-view (alphabet data, other char data, accelerometer) deep learning model, it reaches 93% of identification accuracy in a closed-set scenario of 40 individuals.…”

Section: Related Workmentioning

confidence: 99%

“…The feasibility of such kind of architecture to improve the performance of static keystroke dynamics authentication sys-WIFS'2019, December, [9][10][11][12]2019, Delft, Netherlands. 978-1-7281-3217-4/19/$31.00 c 2019 IEEE.…”

Section: Introductionmentioning

confidence: 99%

Siamese Networks for Static Keystroke Dynamics Authentication

Giot

Rocha

2019

2019 IEEE International Workshop on Information Forensics and Security (WIFS)

View full text Add to dashboard Cite

Keystroke dynamics authentication aims at recognizing individuals on their way of typing on a keyboard. It suffers from a high intra-class variability as any behavioral biometric modality; to provide a large quantity of enrollment samples often overcomes this issue.In this paper, we analyze the feasibility of using siamese networks to rely on biometric samples provided by other users instead of requesting a new user to provide a large number of enrollment samples. Such networks aim at comparing two inputs to compute their similarity: the authentication process consists then at comparing the query to an enrollment sample.The proposed method is compared to several compatible baselines in the literature. Its EER outperforms the best baseline of 28% in a oneshot context and 31% when using 200 enrollment samples. This proves the viability of such approach and opens the path to improvements for using it in other contexts of keystroke dynamics authentication.

show abstract

“…Multi-view learning is a hot idea to think one object with different views [13], [23], [26], [27]. In this paper, we think the HIN with different views such as meta-paths and meta-graph, and fuse the different information for node embedding.…”

Section: Multi-view Learningmentioning

confidence: 99%

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks

Sun¹,

He²,

Huang³

et al. 2018

2018 IEEE International Conference on Big Knowledge (ICBK)

Self Cite

View full text Add to dashboard Cite

Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks, where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph only considers the complex structural information, but ignores its embedded meta-paths information. To address this problem, we propose MEta-GrAph-based network embedding models, called MEGA and MEGA++, respectively. The MEGA model uses normalized relevance or similarity measures that are derived from a meta-graph and its embedded meta-paths between nodes simultaneously, and then leverages tensor decomposition method to perform node embedding. The MEGA++ further facilitates the use of coupled tensor-matrix decomposition method to obtain a joint embedding for nodes, which simultaneously considers the hidden relations of all meta information of a meta-graph. Extensive experiments on two real datasets demonstrate that MEGA and MEGA++ are more effective than state-of-the-art approaches.

show abstract

Sequential Keystroke Behavioral Biometrics for Mobile User Identification via Multi-view Deep Learning

Cited by 50 publications

References 18 publications

Pemetaan Bentuk Dan Pencegahan Penipuan E-Commerce

Pemetaan Bentuk Dan Pencegahan Penipuan E-Commerce

Siamese Networks for Static Keystroke Dynamics Authentication

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks

Contact Info

Product

Resources

About