AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically

Go Generating

AI Traceability

AI parses the academic lineage of this thesis

Generate MRT

AI Insight

AI extracts a summary of this paper

Weibo:

We reported equal error rate for both the Liquid State Machine extracted feature vector and best-reported feature vector from the literature

Toward a continuous authentication system using a biologically inspired machine learning approach - a case study.

SAC, pp.1362-1364, (2019)

Cited by: 0|Views4450

Full Text

View via Publisher

Other Links

dblp.uni-trier.de dl.acm.org academic.microsoft.com

Bibtex

Weibo

Keywords

biologically-inspired computational methods continuous authentication liquid state machine security smartphones

Abstract

Smartphones have recently seen massive growth in usage and become a repository for many types of personal information. The privacy and security are primary concerns for their usage, where there is a need to provide seamless and continuous authentication systems(CASs) for smartphones. We introduce in this work a proof-of-concept design and...More

Code:

Data:

Insight

Full Text

PPT (Upload PPT)

Highlights

The market analysis predicts that in 2020 there will be 6.1 billion smartphones in use worldwide [5]
We reported equal error rate (EER) for both the Liquid State Machine (LSM) extracted feature vector and best-reported feature vector from the literature
This provides more information about how informative the features extracted by LSM are
For long-text and stroke/gesture authentication, we reported EER values for only LSM-extracted feature vector
This work provided a proof-of-concept of using hybrid LSM as a CAS
We showed that the extracted features from LSM are more discriminative than the ones reported in the literature for augmented password authentication Table 2 and 3, while achieving low EER for other types of interactions Table 4, 5, 6 and 7

Tables

Table1: Input types and mappings to aLSM and sLSM
Table2: Augmented Password EER (One vs. One scenario)
Table3: Augmented Password EER (One vs. All)
Table4: Long-Text EER (One vs. One)
Table5: Long-Text EER (One vs. All)
Table6: Gestures/Strokes EER (One vs. One)
Table7: Gestures/Strokes EER (One vs. All)

Download tables as Excel

Funding

The authors thank the Research Board at the American University of Beirut for supporting this work

Study subjects and analysis

users: 22

To do this, first, we designed an Android application to collect and log user interactions with a smartphone. The application was installed on a Samsung GT-i9100 smartphone, and we asked 22 users to participate in data collection. All users are students between 20 to 28 years of age (9 males)

males: 9

The application was installed on a Samsung GT-i9100 smartphone, and we asked 22 users to participate in data collection. All users are students between 20 to 28 years of age (9 males). Each user was asked to perform a 3-step data collection

users: 22

The third step included data collection for strokes/gestures, where the users were asked to swipe anywhere on the screen in a specific direction according to a label that appears on the smartphone’s touchscreen. We tested the framework on the 22 users who participated in the data collection. We reported the results separately for the three types of interactions: augmented password, long-text, and stroke/gesture authentication

Reference

Obada Al Zoubi, Mariette Awad, and Nikola K Kasabov. 2018. Anytime multipurpose emotion recognition from EEG data using a Liquid State Machine based framework. Artificial intelligence in medicine 86 (2018), 1–8.
Kiran S Balagani, Vir V Phoha, Asok Ray, and Shashi Phoha. 2011. On the discriminability of keystroke feature vectors used in fixed text keystroke authentication. Pattern Recognition Letters 32, 7 (2011), 1070–1080.
Jimmy Baraglia, Yukie Nagai, and Minoru Asada. 201Action understanding using an adaptive Liquid State Machine based on environmental ambiguity. In 2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL). IEEE, 1–6.
Harald Burgsteiner. 2006. Imitation learning with spiking neural networks and real-world devices. Engineering Applications of Artificial Intelligence 19, 7 (2006), 741–752.
ERICSSON. 2016. Ericsson Mobility Report for June 2016. https://www.ericsson.com/res/docs/2016/ericsson-mobility-report-2016.pdf
Beata J Grzyb, Eris Chinellato, Grzegorz M Wojcik, and Wieslaw A Kaminski. 2009. Facial expression recognition based on liquid state machines built of alternative neuron models. In 2009 International Joint Conference on Neural Networks. IEEE, 1011–1017.
Yingyezhe Jin and Peng Li. 2016. AP-STDP: A novel self-organizing mechanism for efficient reservoir computing. In Neural Networks (IJCNN), 2016 International Joint Conference on. IEEE, 1158–1165.
Kevin S Killourhy and Roy A Maxion. 2009. Comparing anomaly-detection algorithms for keystroke dynamics. In 2009 IEEE/IFIP International Conference on Dependable Systems & Networks. IEEE, 125–134.
Wolfgang Maass, Thomas Natschläger, and Henry Markram. 2002. Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural computation 14, 11 (2002), 2531–2560.
Jayasree Saha and Rituparna Chaki. 2014. An approach to classify keystroke patterns for remote user authentication. Journal of Medical Informatics & Technologies 23 (2014).
Benjamin Schrauwen, Michiel D’Haene, David Verstraeten, and Jan Van Campenhout. 2008. Compact hardware liquid state machines on FPGA for real-time speech recognition. Neural networks 21, 2 (2008), 511–523.
Qian Wang, Yingyezhe Jin, and Peng Li. 2015. General-purpose LSM learning processor architecture and theoretically guided design space exploration. In Biomedical Circuits and Systems Conference (BioCAS), 2015 IEEE. IEEE, 1–4.

Author

Obada Al Zoubi

Mariette Awad

[0]

Your rating :