EspialCog: General, Efficient and Robust Mobile User Implicit Authentication in Noisy Environment

Zhu, Tiantian; Weng, Zhengqiu; Song, Qijie; Yuan, Chen; Liu, Qiang; Chen, Yan; Lv, Mingqi; Chen, Tieming

doi:10.1109/tmc.2020.3012491

Cited by 9 publications

(28 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different authentication mechanisms can be applied in online learning environments including (1) knowledge based (what a user knows), (2) possession based (what a user has) and (3) biometrics based (what a user is) [3]. Knowledge based authentication using usernames and passwords (also known as password-based) is the most widely applied authentication method, but passwords can potentially be vulnerable and stolen, leading to a failure to authenticate the genuine learner [8][9][10]. The prime example where this is of concern involves academic integrityconsider that learner A (who is the genuine enrolled student) provides their authentication credentials to person B (an imposter), who then completes some or all of the learning activities and assessments required instead of learner A.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Survey of Context-Aware Continuous Implicit Authentication in Online Learning Environments

et al. 2023

View full text Add to dashboard Cite

User authentication is crucial in the digital learning environment to preserve the integrity and reliability of the learning process. Implicit authentication using biometrics has been proposed to improve the user experience while resolving the issues that password dominant authentication faces. Implicit authentication does not require explicit user actions as it is a background process that implicitly acquires a user's identifying information through sensors embedded within the authenticating devices. To accommodate a variety of user contexts, context-aware implicit authentication has gained attention especially in the mobile device domain, but it has not been fully explored in digital learning environments. This study is motivated to determine how implicit authentication can observe students' behaviour without causing disruption to the learning activity. The study provides a structured systematic review of the existing literature to identify and discuss the structure of context-aware continuous implicit authentication systems and future directions. The study found that requirements in the future will be: 1) to consider diverse authenticators to cover all possible user interactions with online learning environments, including coverage of course participants not engaged with online exams; 2) to investigate template adaptation to overcome template ageing issues with biometrics; and 3) to explore evaluation approaches of context-aware implicit authentication systems.

show abstract

Section: Introductionmentioning

confidence: 99%

A Comprehensive Survey of Context-Aware Continuous Implicit Authentication in Online Learning Environments

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The deep metric learning model in [6] is implemented with the deep learning framework Keras, and the two-stream deep learning model in [21] is implemented with the PyTorch framework. [47], Li et al [22], Wang et al [39], and Shen et al [32]. Table 4 lists the sensors, classifiers, training data, experimental result, and time overhead of each representative work.…”

Section: Comparison With Representative Continuous Authentication Met...mentioning

confidence: 99%

“…Experimental results shown that the proposed authentication method can achieve an mean EER of 5.14% with approximately 3s authentication time. Zhu et al [47] applied an optimized LSTM architecture to learn the behavioral patterns from three built-in sensors. Besides, they evaluated the performance of the proposed continuous authentication method on a large-scale real-world noisy dataset.…”

Section: Comparison With Representative Continuous Authentication Met...mentioning

confidence: 99%

“…Although the current methods based on traditional machine learning or deep learning have made some exciting progress, they still suffer some limitations. First, sensory data from impostors (negative samples) are needed to train the continuous authentication model (binary classification or multi-classification) [1,6,11,12,15,21,39,47], since the distribution of negative training data from diverse attackers are unknown, it is a difficult problem to solve in a real-world scenario. Besides, sharing of other smartphone users' biometric data (negative samples) may lead to the leakage of biometric data.…”

Section: Introductionmentioning

confidence: 99%

“…Based on the extracted deep features, they choose the one-class SVM as the classifier. Third, the authentication model's weak capability of capturing Relative Attention-based One-Class Adversarial Autoencoder for Continuous Authentication of Smartphone Users 3 smartphone users' behavioral patterns from sensor data leads to unsatisfactory authentication performance [20,30,32,34,39,44,46,47]. Shen et al [30] construct 48 statistical features from each sensor to represent the smartphone user's behavioral patterns and authenticate his identity.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Relative Attention-based One-Class Adversarial Autoencoder for Continuous Authentication of Smartphone Users

Hu¹,

Zhang²,

You³

et al. 2022

Preprint

View full text Add to dashboard Cite

Behavioral biometrics-based continuous authentication is a promising authentication scheme, which uses behavioral biometrics recorded by built-in sensors to authenticate smartphone users throughout the session. However, current continuous authentication methods suffer some limitations: 1) behavioral biometrics from impostors are needed to train continuous authentication models. Since the distribution of negative samples from diverse attackers are unknown, it is a difficult problem to solve in real-world scenarios; 2) most deep learningbased continuous authentication methods need to train two models to improve authentication performance. A deep learning model for deep feature extraction, and a machine learning-based classifier for classification; 3) weak capability of capturing users' behavioral patterns leads to poor authentication performance. To solve these issues, we propose a relative attention-based one-class adversarial autoencoder for continuous authentication of smartphone users. First, we propose a one-class adversarial autoencoder to learn latent representations of legitimate users' behavioral patterns, which is trained only with legitimate smartphone users' behavioral biometrics. Second, we present the relative attention layer to capture richer contextual semantic representation of users' behavioral patterns, which modifies the standard self-attention mechanism using convolution projection instead of linear projection to perform the attention maps. Experimental results demonstrate that we can achieve superior performance of 1.05% EER, 1.09% EER, and 1.08% EER with a high authentication frequency (0.7s) on three public datasets.CCS Concepts: • Security and privacy → Biometrics; • Human-centered computing → Collaborative and social computing;

show abstract

WebSmell: An Efficient Malicious HTTP Traffic Detection Framework Using Data Augmentation

Chen

Weng

Chen

et al. 2021

Information Security and Cryptology

View full text Add to dashboard Cite

EspialCog: General, Efficient and Robust Mobile User Implicit Authentication in Noisy Environment

Cited by 9 publications

References 39 publications

A Comprehensive Survey of Context-Aware Continuous Implicit Authentication in Online Learning Environments

A Comprehensive Survey of Context-Aware Continuous Implicit Authentication in Online Learning Environments

Relative Attention-based One-Class Adversarial Autoencoder for Continuous Authentication of Smartphone Users

WebSmell: An Efficient Malicious HTTP Traffic Detection Framework Using Data Augmentation

Contact Info

Product

Resources

About