Implicit smartphone authentication via multimodal data and transfer autoencoders

XU Zi’ang

doi:10.11959/j.issn.2096-3750.2025.00493

您当前的位置：

首页 >

文章列表页 >

Implicit smartphone authentication via multimodal data and transfer autoencoders

Theory and Technology | 更新时间：2026-01-26

- Implicit smartphone authentication via multimodal data and transfer autoencoders
- Chinese Journal on Internet of Things Vol. 9, Issue 3, Pages: 93-103(2025)
- 作者机构：
  
  北方工业大学伦敦布鲁内尔学院，北京 100144
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-3750.2025.00493
  CLC： TP309；TP391.4
- Received：13 March 2025，
  
  Revised：2025-06-07，
  
  Published：10 September 2025
- 稿件说明：
移动端阅览
许子昂.基于迁移自编码器与多模态数据的智能手机隐式身份认证[J].物联网学报,2025,09(03):93-103.

XU Zi’ang.Implicit smartphone authentication via multimodal data and transfer autoencoders[J].Chinese Journal on Internet of Things,2025,09(03):93-103.
许子昂.基于迁移自编码器与多模态数据的智能手机隐式身份认证[J].物联网学报,2025,09(03):93-103. DOI： 10.11959/j.issn.2096-3750.2025.00493.

XU Zi’ang.Implicit smartphone authentication via multimodal data and transfer autoencoders[J].Chinese Journal on Internet of Things,2025,09(03):93-103. DOI： 10.11959/j.issn.2096-3750.2025.00493.

摘要

随着智能手机的普及，传统显式身份认证技术（如密码、指纹）因依赖用户主动输入而易受攻击，非侵入式的隐式身份认证逐渐成为研究热点。提出一种基于数据驱动迁移自编码器的智能手机隐式身份认证方案，通过多模态传感器采集用户解锁图案时的行为特征（如加速度、陀螺仪数据），结合自编码器提取高判别性隐层特征，并设计迁移学习框架实现快速模型微调。实验表明，在50位用户、4台智能手机上进行图案解锁时产生的多达10 GB离线数据集上预训练后，仅需1.3 s即可完成在线认证，准确率高达99.06%，显著优于传统机器学习方法（SVM准确率89.19%）、传统深度学习方法（KNN准确率95.49%）及现有SOTA方案（EspialCog准确率98.76%）。此外，用户在使用前仅须录入6次解锁行为即可完成模型适配，兼顾安全性与用户体验。

Abstract

With the widely used of smartphones

traditional explicit authentication methods (e.g.

passwords

fingerprints) are increasingly vulnerable due to their reliance on active user input

making the non-invasive implicit authentication a critical research focus. A transfer autoencoder-based implicit authentication framework for smartphones was proposed. Users’ behavioral features were captured during pattern unlocking (e.g.

accelerometer and gyroscope data) through multimodal sensors

an autoencoder was employed to extract discriminative latent representations

and a transfer learning mechanism was incorporated for rapid model fine-tuning. The results of the experiment indicate that following the pre-training of the scheme on a 10 GB offline dataset

which is generated from the unlocking patterns of 50 users across 4 smartphones

the online authentication process can be executed in a mere 1.3 seconds

achieving an accuracy rate of 99.06%. This performance is markedly superior to that of traditional machine learning methods

such as support vector machine (SVM)

which exhibits an accuracy rate of 89.19%. Furthermore

it surpasses conventional deep learning approaches

including K-nearest neighbor (KNN) with an accuracy of 95.49%

as well as existing state-of-the-art (SOTA) schemes like EspialCog

which achieves an accuracy of 98.76%. Additionally

it is noteworthy that users are required to perform the unlocking behavior only six times prior to utilization in order to complete the model adaptation

thereby balancing considerations of security with user experience.

关键词

Keywords

references

CHECK POINT . Global cybersecurity trends in 2025 [R ] . 2015 .

YIN X F , WANG S , SHAHZAD M , et al . An IoT-oriented privacy-preserving fingerprint authentication system [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 14 ): 11760 - 11771 .

PAPAIOANNOU M , PELEKOUDAS-OIKONOMOU F , MANTAS G , et al . A survey on quantitative risk estimation approaches for secure and usable user authentication on smartphones [J ] . Sensors , 2023 , 23 ( 6 ): 2979 .

FERRAG M A , MAGLARAS L , DERHAB A , et al . Authentication schemes for smart mobile devices: threat models, countermeasures, and open research issues [J ] . Telecommunication Systems , 2020 , 73 ( 2 ): 317 - 348 .

兰贞 . 智能终端的隐式身份认证方法研究 [D ] . 杭州 : 浙江大学 , 2022 .

LAN Z . Research on implicit user authentication methods of smart terminals [D ] . Hangzhou : Zhejiang University , 2022 .

金瑜瑶 , 张晓梅 . 基于多尺度卷积和LSTM的多模态隐式认证 [J ] . 智能计算机与应用 , 2023 , 13 ( 12 ): 87 - 92 .

JIN Y Y , ZHANG X M . Implicit authentication of multi-modal based on multi-scale convolution and LSTM [J ] . Intelligent Computer and Applications , 2023 , 13 ( 12 ): 87 - 92 .

姚睿 . 基于步态行为的移动终端隐式身份认证方法研究 [D ] . 北京 : 北京邮电大学 , 2022 .

YAO R . Research and implement of identity authentication technology based on user behavior analysis [D ] . Beijing : Beijing University of Posts and Telecommunications , 2022 .

WU C , HE K , CHEN J , et al . CaIAuth: context-aware implicit authentication when the screen is awake [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 12 ): 11420 - 11430 .

KARANIKIOTIS T , PAPAMICHAIL M D , CHATZIDIMITRIOU K C , et al . Continuous implicit authentication through touch traces modelling [C ] // Proceedings of the 2020 IEEE 20th International Conference on Software Quality, Reliability and Security (QRS) . Piscataway : IEEE Press , 2020 : 111 - 120 .

VHADURI S , DIBBO S V , CHEUNG W . HIAuth: a hierarchical implicit authentication system for IoT wearables using multiple biometrics [J ] . IEEE Access , 2021 , 9 : 116395 - 116406 .

ABUHAMAD M , ABUHMED T , MOHAISEN D , et al . AUToSen: deep-learning-based implicit continuous authentication using smartphone sensors [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 6 ): 5008 - 5020 .

ZHANG J H , LI Z C , ZHANG H C , et al . Sensor-based implicit authentication through learning user physiological and behavioral characteristics [J ] . Computer Communications , 2023 , 208 : 244 - 255 .

EKIZ D , CAN Y S , DARDAGAN Y C , et al . Can a smartband be used for continuous implicit authentication in real life [J ] . IEEE Access , 2020 , 8 : 59402 - 59411 .

MASSOLI F V , CARRARA F , AMATO G , et al . Detection of face recognition adversarial attacks [J ] . Computer Vision and Image Understanding , 2021 , 202 : 103103 .

ZHU T T , WENG Z Q , SONG Q J , et al . EspialCog: general, efficient and robust mobile user implicit authentication in noisy environment [J ] . IEEE Transactions on Mobile Computing , 2022 , 21 ( 2 ): 555 - 572 .

WU C X , LI X P , ZUO F , et al . Use it-no need to shake it! [C ] // Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies New York: ACM Press , 2022 , 6 ( 3 ): 1 - 25 .

ZENG X , ZHANG X M , YANG S Q , et al . Gait-based implicit authentication using edge computing and deep learning for mobile devices [J ] . Sensors , 2021 , 21 ( 13 ): 4592 .

ZHAO C M , GAO F , SHEN Z H . AttAuth: an implicit authentication framework for smartphone users using multimodality data [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 4 ): 6928 - 6942 .

RYU R , YEOM S , HERBERT D , et al . A comprehensive survey of context-aware continuous implicit authentication in online learning environments [J ] . IEEE Access , 2023 , 11 : 24561 - 24573

LI Y T , OUYANG C K , HUANG H Y . AEGANAuth: autoencoder GAN-based continuous authentication with conditional variational autoencoder generative adversarial network [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 16 ): 27635 - 27650 .

吴美君 , 杨新 , 潘超凡 , 等 . 自编码器结合持续学习: 现状、挑战与展望 [J ] . 计算机学报 , 2025 , 48 ( 2 ): 317 - 357

WU M J , YANG X , PAN C F , et al . Autoencoders combined with continual learning: development, challenges, and prospects [J ] . Chinese Journal of Computers , 2025 , 48 ( 2 ): 317 - 357 .

富坤 , 孙明磊 , 郝玉涵 , 等 . 基于对抗训练的伪标签约束自编码器 [J ] . 计算机工程 , 2023 , 49 ( 11 ): 123 - 130 .

FU K , SUN M L , HAO Y H , et al . Adversarial training based pseudo label constraint auto-encoder [J ] . Computer Engineering , 2023 , 49 ( 11 ): 123 - 130 .

孙仁科 , 许靖昊 , 皇甫志宇 , 等 . 基于视觉-语言预训练模型的零样本迁移学习方法综述 [J ] . 计算机工程 , 2024 , 50 ( 10 ): 1 - 15 .

SUN R K , XU J H , HUANGFU Z Y , et al . Survey of zero-shot transfer learning methods based on vision-language pre-trained models [J ] . Computer Engineering , 2024 , 50 ( 10 ): 1 - 15 .

黄超 , 程春玲 , 王有康 . 基于伪标签不确定性估计的无源域自适应方法 [J ] . 计算机科学 , 2024 : 1 - 11 .

HUANG C , CHENG C L , WANG Y K . Passive domain adaptive method based on pseudo-label uncertainty estimation [J ] . Computer Science , 2024 : 1- 11 ..

文利燕 , 陈金陵 , 姜斌 , 等 . 基于联合对抗域自适应网络的跨工况故障诊断方法 [J ] . 控制与决策 , 2025 , 40 ( 5 ): 1503 - 1511 .

WEN L Y , CHEN J L , JIANG B , et al . A joint adversarial domain adaptive network based cross working conditions fault diagnosis method [J ] . Control and Decision , 2025 , 40 ( 5 ): 1503 - 1511 .

MUANDET K , FUKUMIZU K , SRIPERUMBUDUR B , et al . Kernel mean embedding of distributions: a review and beyond [J ] . Foundations and Trends® in Machine Learning , 2017 , 10 ( 1/2 ): 1 - 141 .

孟小峰 , 王雷霞 , 刘俊旭 . 人工智能时代的数据隐私、垄断与公平 [J ] . 大数据 , 2020 , 6 ( 1 ): 35 - 46 .

MENG X F , WANG L X , LIU J X . Data privacy, monopoly and fairness for AI [J ] . Big Data Research , 2020 , 6 ( 1 ): 35 - 46 .

张燕 , 杨一帆 , 伊人 , 等 . 隐私计算场景下数据质量治理探索与实践 [J ] . 大数据 , 2022 , 8 ( 5 ): 55 - 73 .

ZHANG Y , YANG Y F , YI R , et al . Exploration and practice of data quality governance in privacy computing scenarios [J ] . Big Data Research , 2022 , 8 ( 5 ): 55 - 73 .

林梦琪 , 张晓梅 . 基于行为足迹的多模态融合身份认证 [J ] . 计算机工程 , 2021 , 47 ( 10 ): 116 - 124 .

LIN M Q , ZHANG X M . Identity authentication of multi-modal fusion based on behavioral footprint [J ] . Computer Engineering , 2021 , 47 ( 10 ): 116 - 124 .

李茜 . 基于特征融合的分布式持续身份认证研究 [D ] . 西安 : 西安电子科技大学 , 2022 .

LI Q . Research on distributed continuous authentication based on feature fusion [D ] . Xi’an : Xidian University , 2022 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Intelligent compression and feedback technology for multi-node collaborative ISAC

Siamese GCN empowered fingerprinting indoor localization using few-shot transfer learning

A transfer reinforcement learning-based approach for cross-domain charging station recommendation in the Internet of vehicles

Privacy cloud storage scheme based on fog computing

A Survey on Data Security and Privacy Protection for Large Models

Related Author

SHEN Luyao

XIA wenchao

LOU Xingliang

CHEN Lu

GU Hao

ZHU Hongbo

ZHAO Haitao

XIA Wenchao

Related Institution

the Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks, Ministry of Education,Nanjing University of Posts and Telecommunications

Jiangsu Provincial Key Laboratory of Wireless Communications and IoT, Nanjing University of Posts and Telecommunications

School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications

School of Integrated Circuits, Southeast University

Jiangsu Province Key Laboratory of Wireless Communication and Internet of Things

⁰