This research aims to further understanding in the field of continuous
authentication using behavioral biometrics. We are contributing a novel dataset
that encompasses the gesture data of 15 users playing Minecraft with a Samsung
Tablet, each for a duration of 15 minutes. Utilizing this dataset, we employed
machine learning (ML) binary classifiers, being Random Forest (RF), K-Nearest
Neighbors (KNN), and Support Vector Classifier (SVC), to determine the
authenticity of specific user actions. Our most robust model was SVC, which
achieved an average accuracy of approximately 90%, demonstrating that touch
dynamics can effectively distinguish users. However, further studies are needed
to make it viable option for authentication systems

本研究旨在进一步研究利用行为生物特征进行连续身份验证的领域。我们贡献了一个创新的数据集，该数据集涵盖了 15 名用户使用三星平板电脑玩 Minecraft 的手势数据，每个用户游戏时间为 15 分钟。利用这个数据集，我们使用了机器学习二元分类器，包括随机森林、K 最近邻和支持向量分类器，来确定特定用户行为的真实性。我们最强大的模型是支持向量分类器，其平均准确率达到了约 90%，表明触摸动态可以有效区分用户。然而，还需要进一步研究使其成为身份验证系统的可行选择。

您的设备可能比您自己更了解您 —— 使用机器学习在新数据集上进行连续认证

Your device may know you better than you know yourself -- continuous  authentication on novel dataset using machine learning

We present a novel adversarial model for authentication systems that use gait
patterns recorded by the inertial measurement unit (IMU) built into
smartphones. The attack idea is inspired by and named after the concept of a
dictionary attack on knowledge (PIN or password) based authentication systems.
In particular, this work investigates whether it is possible to build a
dictionary of IMUGait patterns and use it to launch an attack or find an
imitator who can actively reproduce IMUGait patterns that match the target's
IMUGait pattern. Nine physically and demographically diverse individuals walked
at various levels of four predefined controllable and adaptable gait factors
(speed, step length, step width, and thigh-lift), producing 178 unique IMUGait
patterns. Each pattern attacked a wide variety of user authentication models.
The deeper analysis of error rates (before and after the attack) challenges the
belief that authentication systems based on IMUGait patterns are the most
difficult to spoof; further research is needed on adversarial models and
associated countermeasures.

我们提出了一种新颖的对抗模型，用于使用智能手机内置的惯性测量单元（IMU）记录的步态模式进行身份验证系统。该模型探索了构建 IMUGait 模式字典并使用其发起攻击或找到能够主动重现与目标的 IMUGait 模式匹配的模仿者是否可能。

基于 IMU 的步态认证的字典攻击

Dictionary Attack on IMU-based Gait Authentication

Federated learning (FL) is a promising approach for enhancing data privacy
preservation, particularly for authentication systems. However, limited round
communications, scarce representation, and scalability pose significant
challenges to its deployment, hindering its full potential. In this paper, we
propose 'ProtoFL', Prototypical Representation Distillation based unsupervised
Federated Learning to enhance the representation power of a global model and
reduce round communication costs. Additionally, we introduce a local one-class
classifier based on normalizing flows to improve performance with limited data.
Our study represents the first investigation of using FL to improve one-class
classification performance. We conduct extensive experiments on five widely
used benchmarks, namely MNIST, CIFAR-10, CIFAR-100, ImageNet-30, and
Keystroke-Dynamics, to demonstrate the superior performance of our proposed
framework over previous methods in the literature.

我们提出了 'ProtoFL'，基于原型表示蒸馏的无监督联邦学习，以增强全局模型的表示能力并降低往返通信成本，同时引入基于归一化流的本地一类分类器以改善有限数据的性能。我们在 MNIST、CIFAR-10、CIFAR-100、ImageNet-30 和 Keystroke-Dynamics 等五个广泛使用的基准测试上进行了大量实验，以展示我们提出的框架在文献中的先前方法上的卓越性能。