arXiv subjects

Ruben Vera-Rodriguez

Publications and source records attributed to Ruben Vera-Rodriguez.

81 records · Page 5Linked to original sources

arXiv2020

BeCAPTCHA: Detecting Human Behavior in Smartphone Interaction using Multiple Inbuilt Sensors

We introduce a novel multimodal mobile database called HuMIdb (Human Mobile Interaction database) that comprises 14 mobile sensors acquired from 600 users. The heterogeneous flow of data generated during the interaction with the smartphones can be used to model human behavior when interacting with the technology. Based on this new dataset, we explore the capacity of smartphone sensors to improve bot detection. We propose a CAPTCHA method based on the analysis of the information obtained during a single drag and drop task. We evaluate the method generating fake samples synthesized with Generative Adversarial Neural Networks and handcrafted methods. Our results suggest the potential of mobile sensors to characterize the human behavior and develop a new generation of CAPTCHAs.

cs.HC↗

arXiv2020

Keystroke Biometrics in Response to Fake News Propagation in a Global Pandemic

This work proposes and analyzes the use of keystroke biometrics for content de-anonymization. Fake news have become a powerful tool to manipulate public opinion, especially during major events. In particular, the massive spread of fake news during the COVID-19 pandemic has forced governments and companies to fight against missinformation. In this context, the ability to link multiple accounts or profiles that spread such malicious content on the Internet while hiding in anonymity would enable proactive identification and blacklisting. Behavioral biometrics can be powerful tools in this fight. In this work, we have analyzed how the latest advances in keystroke biometric recognition can help to link behavioral typing patterns in experiments involving 100,000 users and more than 1 million typed sequences. Our proposed system is based on Recurrent Neural Networks adapted to the context of content de-anonymization. Assuming the challenge to link the typed content of a target user in a pool of candidate profiles, our results show that keystroke recognition can be used to reduce the list of candidate profiles by more than 90%. In addition, when keystroke is combined with auxiliary data (such as location), our system achieves a Rank-1 identification performance equal to 52.6% and 10.9% for a background candidate list composed of 1K and 100K profiles, respectively.

cs.CR↗

arXiv2020

TypeNet: Scaling up Keystroke Biometrics

We study the suitability of keystroke dynamics to authenticate 100K users typing free-text. For this, we first analyze to what extent our method based on a Siamese Recurrent Neural Network (RNN) is able to authenticate users when the amount of data per user is scarce, a common scenario in free-text keystroke authentication. With 1K users for testing the network, a population size comparable to previous works, TypeNet obtains an equal error rate of 4.8% using only 5 enrollment sequences and 1 test sequence per user with 50 keystrokes per sequence. Using the same amount of data per user, as the number of test users is scaled up to 100K, the performance in comparison to 1K decays relatively by less than 5%, demonstrating the potential of TypeNet to scale well at large scale number of users. Our experiments are conducted with the Aalto University keystroke database. To the best of our knowledge, this is the largest free-text keystroke database captured with more than 136M keystrokes from 168K users.

cs.CV↗

arXiv2020

Blockchain meets Biometrics: Concepts, Application to Template Protection, and Trends

Blockchain technologies provide excellent architectures and practical tools for securing and managing the sensitive and private data stored in biometric templates, but at a cost. We discuss opportunities and challenges in the integration of blockchain and biometrics, with emphasis in biometric template storage and protection, a key problem in biometrics still largely unsolved. Key tradeoffs involved in that integration, namely, latency, processing time, economic cost, and biometric performance are experimentally studied through the implementation of a smart contract on the Ethereum blockchain platform, which is publicly available in github for research purposes.

cs.CV↗

arXiv2020

Exploiting Complexity in Pen- and Touch-based Signature Biometrics

Biometric signature verification has been traditionally performed in pen-based office-like scenarios using devices specifically designed for acquiring handwriting. However, the high deployment of devices such as smartphones and tablets has given rise to new and thriving scenarios for signature biometrics where handwriting can be performed using not only a pen stylus but also the finger via touch interaction. Some preliminary studies have highlighted the challenge of this new scenario and the necessity of further research on the topic. The main contribution of this work is to propose a new on-line signature verification architecture adapted to the signature complexity in order to tackle this new and challenging scenario. Additionally, an exhaustive comparative analysis of both pen- and touch-based scenarios using our proposed methodology is carried out along with a review of the most relevant and recent studies in the field. Significant improvements of biometric verification performance and practical insights are extracted for the application of signature verification in real scenarios.

cs.HC↗

arXiv2020

BioTouchPass2: Touchscreen Password Biometrics Using Time-Aligned Recurrent Neural Networks

Passwords are still used on a daily basis for all kind of applications. However, they are not secure enough by themselves in many cases. This work enhances password scenarios through two-factor authentication asking the users to draw each character of the password instead of typing them as usual. The main contributions of this study are as follows: i) We present the novel MobileTouchDB public database, acquired in an unsupervised mobile scenario with no restrictions in terms of position, posture, and devices. This database contains more than 64K on-line character samples performed by 217 users, with 94 different smartphone models, and up to 6 acquisition sessions. ii) We perform a complete analysis of the proposed approach considering both traditional authentication systems such as Dynamic Time Warping (DTW) and novel approaches based on Recurrent Neural Networks (RNNs). In addition, we present a novel approach named Time-Aligned Recurrent Neural Networks (TA-RNNs). This approach combines the potential of DTW and RNNs to train more robust systems against attacks. A complete analysis of the proposed approach is carried out using both MobileTouchDB and e-BioDigitDB databases. Our proposed TA-RNN system outperforms the state of the art, achieving a final 2.38% Equal Error Rate, using just a 4-digit password and one training sample per character. These results encourage the deployment of our proposed approach in comparison with traditional typed-based password systems where the attack would have 100% success rate under the same impostor scenario.

cs.CV↗

arXiv2019

Biometric Template Storage with Blockchain: A First Look into Cost and Performance Tradeoffs

We explore practical tradeoffs in blockchain-based biometric template storage. We first discuss opportunities and challenges in the integration of blockchain and biometrics, with emphasis in biometric template storage and protection, a key problem in biometrics still largely unsolved. Blockchain technologies provide excellent architectures and practical tools for securing and managing the sensitive and private data stored in biometric templates, but at a cost. We explore experimentally the key tradeoffs involved in that integration, namely: latency, processing time, economic cost, and biometric performance. We experimentally study those factors by implementing a smart contract on Ethereum for biometric template storage, whose cost-performance is evaluated by varying the complexity of state-of-the-art schemes for face and handwritten signature biometrics. We report our experiments using popular benchmarks in biometrics research, including deep learning approaches and databases captured in the wild. As a result, we experimentally show that straightforward schemes for data storage in blockchain (i.e., direct and hash-based) may be prohibitive for biometric template storage using state-of-the-art biometric methods. A good cost-performance tradeoff is shown by using a blockchain approach based on Merkle trees.

cs.CR↗

arXiv2019

Blockchain and Biometrics: A First Look into Opportunities and Challenges

Blockchain technology has become a thriving topic in the last years, making possible to transform old-fashioned operations to more fast, secured, and cheap approaches. In this study we explore the potential of blockchain for biometrics, analyzing how both technologies can mutually benefit each other. The contribution of this study is twofold: 1) we provide a short overview of both blockchain and biometrics, focusing on the opportunities and challenges that arise when combining them, and 2) we discuss in more detail blockchain for biometric template protection.

cs.CR↗

arXiv2019

MultiLock: Mobile Active Authentication based on Multiple Biometric and Behavioral Patterns

In this paper we evaluate mobile active authentication based on an ensemble of biometrics and behavior-based profiling signals. We consider seven different data channels and their combination. Touch dynamics (touch gestures and keystroking), accelerometer, gyroscope, WiFi, GPS location and app usage are all collected during human-mobile interaction to authenticate the users. We evaluate two approaches: one-time authentication and active authentication. In one-time authentication, we employ the information of all channels available during one session. For active authentication we take advantage of mobile user behavior across multiple sessions by updating a confidence value of the authentication score. Our experiments are conducted on the semi-uncontrolled UMDAA-02 database. This database comprises smartphone sensor signals acquired during natural human-mobile interaction. Our results show that different traits can be complementary and multimodal systems clearly increase the performance with accuracies ranging from 82.2% to 97.1% depending on the authentication scenario.

cs.CR↗