TypeFormer: Transformers for Mobile Keystroke Biometrics

Stragapede, Giuseppe; Delgado-Santos, Paula; Tolosana, Rubén; Vera-Rodríguez, Rubén; Guest, Richard; Morales, Aythami

doi:10.48550/arxiv.2212.13075

Cited by 3 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 1, some of the most important public keystroke dynamics databases are reported in chronological order. Although the literature on keystroke biometrics is extensive, to the best of our knowledge, except very few cases [11], [16], previous systems have mostly been only evaluated with up to several hundred subjects not representing well the recent challenges that massive usage applications can face. In addition, most research works are mainly focused only on desktop and fixedtext scenarios.…”

Section: B Limitations Of Existing Evaluation Methodologiesmentioning

confidence: 99%

“…To create the framework, we consider two of the largest public databases of keystroke dynamics up to date, the Aalto Desktop [25] and Mobile [26] Keystroke Databases, extracting datasets that guarantee a minimum amount of data per subject, age and gender annotations, absence of corrupted data, and that avoid too unbalanced subject distributions with respect to the considered demographic attributes. • We illustrate the main aspects of the proposed framework by considering two recent state-of-the-art keystroke biometric systems, TypeNet [11], and Type-Former [16], [43]. To this end, we propose a thorough analysis considering four different sets of features (Sec.…”

Section: Contributionsmentioning

confidence: 99%

“…Sec. V provides an overview of the two biometric systems, TypeNet [11] and TypeFormer [16], utilized to validate the framework, followed by Sec. VI, in which the set of experiments for privacy-enhancement is illustrated.…”

Section: Contributionsmentioning

confidence: 99%

“…Based on the described evaluation design, following [11], [16], we consider two cases for evaluating the system:…”

Section: Evaluation Descriptionmentioning

confidence: 99%

See 3 more Smart Citations

Keystroke Verification Challenge (KVC): Biometric and Fairness Benchmark Evaluation

Stragapede,

Vera-Rodriguez,

Tolosana

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Analyzing keystroke dynamics (KD) for biometric verification has several advantages: it is among the most discriminative behavioral traits; keyboards are among the most common human-computer interfaces, being the primary means for users to enter textual data; its acquisition does not require additional hardware, and its processing is relatively lightweight; and it allows for transparently recognizing subjects. However, the heterogeneity of experimental protocols and metrics, and the limited size of the databases adopted in the literature impede direct comparisons between different systems, thus representing an obstacle in the advancement of keystroke biometrics. To alleviate this aspect, we present a new experimental framework to benchmark KD-based biometric verification performance and fairness based on tweet-long sequences of variable transcript text from over 185,000 subjects, acquired through desktop and mobile keyboards, extracted from the Aalto Keystroke Databases. The framework runs on CodaLab in the form of the Keystroke Verification Challenge (KVC) a . Moreover, we also introduce a novel fairness metric, the Skewed Impostor Ratio (SIR), to capture inter-and intra-demographic group bias patterns in the verification scores. We demonstrate the usefulness of the proposed framework by employing two state-of-the-art keystroke verification systems, TypeNet and TypeFormer, to compare different sets of input features, achieving a less privacy-invasive system, by discarding the analysis of text content (ASCII codes of the keys pressed) in favor of extended features in the time domain. Our experiments show that this approach allows to maintain satisfactory performance.

show abstract

Section: B Limitations Of Existing Evaluation Methodologiesmentioning

confidence: 99%

Section: Contributionsmentioning

confidence: 99%

Section: Contributionsmentioning

confidence: 99%

“…Based on the described evaluation design, following [11], [16], we consider two cases for evaluating the system:…”

Section: Evaluation Descriptionmentioning

confidence: 99%

See 2 more Smart Citations

Keystroke Verification Challenge (KVC): Biometric and Fairness Benchmark Evaluation

Stragapede,

Vera-Rodriguez,

Tolosana

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Mao, Wang, and Ji [46] combined keystroke content with keystroke time as the feature vector using a CNN to process the feature vectors and then input the normalized vector into the bi-LSTM network for training; they then tested this approach on an open data set and achieved an FRR, FAR, and EER of 3.09%, 3.03%, and 4.23%, respectively. Stragapede, Delgado-Santos, Tolosana, Vega-Rodriguez, Guest, and Morales [47] took into account the emotional and physical state of the authenticator and proposed a novel transformer architecture to model free-text KD performed on mobile devices using a publicly available Aalto mobile keystroke database, and they achieved experimental results that outperformed the current state-of-the-art systems, with an EER of 3.25% from only five enrollment sessions of 50 keystrokes each.…”

Section: Behavioral Authentication Using MLmentioning

confidence: 99%

A Secure and Scalable Behavioral Dynamics Authentication Model

Oladipo,

Awotunde,

Nicho

et al. 2023

IJACSA

View full text Add to dashboard Cite

Various authentication methods have been proposed to mitigate data breaches. However, the increasing frequency of data breaches and users' lack of awareness have exposed traditional methods, including single-factor passwordbased systems and, two-factor authentication systems, to vulnerabilities against attacks. While behavioral authentication holds promise in tackling these issues, it faces challenges concerning interoperability between operating systems, the security of behavioral data, accuracy enhancement, scalability, and cost. This research presents a scalable dynamic behavioral authentication model utilizing keystroke typing patterns. The model is constructed around five key components: humancomputer interface devices, encryption of behavioral data, consideration of the authenticator's emotional state, incorporation of cross-platform features, and proposed implementation solutions. It addresses potential typing errors and employs data encryption for behavioral data, achieving a harmonious blend of usability and security by leveraging keyboard dynamics. This is accomplished through the implementation of a web-based authentication system that integrates Convolutional Neural Networks (CNNs) for advanced feature engineering. Keystroke typing patterns were gathered from participants and subsequently employed to evaluate the system's keystroke timing verification, login ID verification, and error handling capabilities. The web-based system uniquely identifies users by merging their username-password (UN-PW) credentials with their keyboard typing patterns, all while securely storing the keystroke data. Given the achievement of a 100% accuracy rate, the proposed Behavioral Dynamics Authentication Model (BDA) introduces future researchers to five scalable constructs. These constructs offer an optimal combination, tailored to the device and context, for maximizing effectiveness. This achievement underscores its potential applications in the realm of authentication.

show abstract

DoubleStrokeNet: Bigram-Level Keystroke Authentication

Neacsu,

Poncu,

Ruseti

et al. 2023

Electronics

View full text Add to dashboard Cite

Keystroke authentication is a well-established biometric technique that has gained significant attention due to its non-intrusive and continuous characteristics. The method analyzes the unique typing patterns of individuals to verify their identity while interacting with the keyboard, both virtual and hardware. Current deep-learning approaches like TypeNet and TypeFormer focus on generating biometric signatures as embeddings for the entire typing sequence. The authentication process is defined using the Euclidean distances between the new typing embedding and the saved biometric signatures. This paper introduces a novel approach called DoubleStrokeNet for authenticating users through keystroke analysis using bigram embeddings. Unlike conventional methods, our model targets the temporal features of bigrams to generate user embeddings. This is achieved using a Transformer-based neural network that distinguishes between different bigrams. Furthermore, we employ self-supervised learning techniques to compute embeddings for both bigrams and users. By harnessing the power of the Transformer’s attention mechanism, the DoubleStrokeNet approach represents a significant departure from existing methods. It allows for a more precise and accurate assessment of user authenticity, specifically emphasizing the temporal characteristics and latent representations of bigrams in deriving user embeddings. Our experiments were conducted using the Aalto University keystrokes datasets, which include 136 million keystrokes from 168,000 subjects using physical keyboards and 63 million keystrokes acquired on mobile devices from 60,000 subjects. The DoubleStrokeNet outperforms the TypeNet-based authentication system using 10 enrollment typing sequences, achieving Equal Error Rate (EER) values of 0.75% and 2.35% for physical and touchscreen keyboards, respectively.

show abstract

TypeFormer: Transformers for Mobile Keystroke Biometrics

Cited by 3 publications

References 0 publications

Keystroke Verification Challenge (KVC): Biometric and Fairness Benchmark Evaluation

Keystroke Verification Challenge (KVC): Biometric and Fairness Benchmark Evaluation

A Secure and Scalable Behavioral Dynamics Authentication Model

DoubleStrokeNet: Bigram-Level Keystroke Authentication

Contact Info

Product

Resources

About