An Overview of Privacy-enhancing Technologies in Biometric Recognition

Melzi, Pietro; Rathgeb, Christian; Tolosana, Rubén; Vera-Rodríguez, Rubén; Busch, Christoph

doi:10.48550/arxiv.2206.10465

Cited by 6 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the ASCII codes are useful for learning relations between time and spatial distributions over the keyboard layout. Nevertheless, although handled in compliance with sensitive data protection regulations [13], they inevitably reveal the content of the text, putting at risk the privacy of the subjects [14], [15]. Other information such as the amount of pressure on the key or the size of the fingertip might be available depending on the specific hardware capabilities.…”

Section: A Keystroke Dynamics For Biometric Recognitionmentioning

confidence: 99%

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: A Keystroke Dynamics For Biometric Recognitionmentioning

confidence: 99%

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

“…Instead, it performs operations on the templates to block the access to such information. On the other hand, the data minimization approach aims to effectively remove the sensitive information from the stored templates [12], [28].…”

Section: Related Workmentioning

confidence: 99%

Gender Privacy Angular Constraints for Face Recognition

Rezgui,

Strisciuglio,

Veldhuis

2024

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Deep learning-based face recognition systems produce templates that encode sensitive information next to identity, such as gender and ethnicity. This poses legal and ethical problems as the collection of biometric data should be minimized and only specific to a designated task. We propose two privacy constraints to hide the gender attribute that can be added to a recognition loss. The first constraint relies on the minimization of the angle between gender-centroid embeddings. The second constraint relies on the minimization of the angle between gender specific embeddings and their opposing gender-centroid weight vectors. Both constraints enforce the overlapping of the gender specific distributions of the embeddings. Furthermore, they have a direct interpretation in the embedding space and do not require a large number of trainable parameters as two fully connected layers are sufficient to achieve satisfactory results. We also provide extensive evaluation results across several datasets and face recognition networks, and we compare our method to three state-ofthe-art methods. Our method is capable of maintaining high verification performances while significantly improving privacy in a cross-database setting, without increasing the computational load for template comparison. We also show that different training data can result in varying levels of effectiveness of privacy-enhancing methods that implement data minimization.

show abstract

“…or individuals' appearance in images, as well as user habits across different data points [47]. Protecting the privacy of such data requires careful attention in line with ethical guidelines and regulations [48], [49].…”

Section: Limitations and Future Workmentioning

confidence: 99%

AI4Food-NutritionFW: A Novel Framework for the Automatic Synthesis and Analysis of Eating Behaviours

Romero-Tapiador,

Tolosana,

Morales

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Leading a healthy lifestyle significantly reduces the risk of developing Non-Communicable Diseases (NCD). However, defining and monitoring healthy eating behaviour depends on multiple factors and usually requires the intervention of experts. On the other hand, nowadays millions of images are shared on social media and web platforms. In particular, many of them are food images taken from a smartphone over time, providing information related to the individual's diet. Consequently, exploiting recent advances in image processing and Artificial Intelligence (AI), this scenario represents an excellent opportunity to: i) create new methods that analyse the individuals' health from what they eat, and ii) develop personalised recommendations to improve nutrition and diet under specific circumstances (e.g., obesity or COVID). This article introduces the AI4Food-NutritionFW, a framework that facilitates the creation of food image datasets tailored to configurable eating behaviours. The framework considers various aspects such as region and lifestyle, simulating a user-friendly scenario where individuals capture food images using their smartphones. The study also presents a novel food image dataset comprising 4,800 diverse weekly diets from 15 distinct profiles, ranging from healthy eating habits to unhealthy ones. Finally, we evaluate the healthy eating behaviours through a score based on the Normalised Mahalanobis Distance (NMD), achieving promising results (99.53% and 99.60% accuracy and sensitivity, respectively). We also release to the research community a software implementation of our proposed AI4Food-NutritionFW a and the mentioned food image dataset created with it.

show abstract

An Overview of Privacy-enhancing Technologies in Biometric Recognition

Cited by 6 publications

References 36 publications

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

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

Gender Privacy Angular Constraints for Face Recognition

AI4Food-NutritionFW: A Novel Framework for the Automatic Synthesis and Analysis of Eating Behaviours

Contact Info

Product

Resources

About