David Sánchez

Rami Haffar, David Sánchez, Josep Domingo-Ferrer

Human facial data offers valuable potential for tackling classification problems, including face recognition, age estimation, gender identification, emotion analysis, and race classification. However, recent privacy regulations, particularly the EU General Data Protection Regulation, have restricted the collection and usage of human images in research. As a result, several previously published face data sets have been removed from the internet due to inadequate data collection methods and privacy concerns. While synthetic data sets have been suggested as an alternative, they fall short of accurately representing the real data distribution. Additionally, most existing data sets are labeled for just a single task, which limits their versatility. To address these limitations, we introduce the Multi-Task Face (MTF) data set, designed for various tasks, including face recognition and classification by race, gender, and age, as well as for aiding in training generative networks. The MTF data set comes in two versions: a non-curated set containing 132,816 images of 640 individuals and a manually curated set with 5,246 images of 240 individuals, meticulously selected to maximize their classification quality. Both data sets were ethically sourced, using publicly available celebrity images in full compliance with copyright regulations. Along with providing detailed descriptions of data collection and processing, we evaluated the effectiveness of the MTF data set in training five deep learning models across the aforementioned classification tasks, achieving up to 98.88\% accuracy for gender classification, 95.77\% for race classification, 97.60\% for age classification, and 79.87\% for face recognition with the ConvNeXT model. Both MTF data sets can be accessed through the following link. https://github.com/RamiHaf/MTF_data_set

Alberto Blanco-Justicia, David Sanchez, Josep Domingo-Ferrer et al.

We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not offer the ex ante privacy guarantees of DP. Instead, what they deliver is basically noise addition similar to the traditional (and often criticized) statistical disclosure control approach. Due to the lack of formal privacy guarantees, the actual level of privacy offered must be experimentally assessed ex post, which is done very seldom. In this respect, we present empirical results showing that standard anti-overfitting techniques in ML can achieve a better utility/privacy/efficiency trade-off than DP.

Najeeb Moharram Jebreel, Josep Domingo-Ferrer, David Sánchez et al.

Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in their devices. However, that same autonomy opens the door for malicious peers to poison the model by conducting either untargeted or targeted poisoning attacks. The label-flipping (LF) attack is a targeted poisoning attack where the attackers poison their training data by flipping the labels of some examples from one class (i.e., the source class) to another (i.e., the target class). Unfortunately, this attack is easy to perform and hard to detect and it negatively impacts on the performance of the global model. Existing defenses against LF are limited by assumptions on the distribution of the peers' data and/or do not perform well with high-dimensional models. In this paper, we deeply investigate the LF attack behavior and find that the contradicting objectives of attackers and honest peers on the source class examples are reflected in the parameter gradients corresponding to the neurons of the source and target classes in the output layer, making those gradients good discriminative features for the attack detection. Accordingly, we propose a novel defense that first dynamically extracts those gradients from the peers' local updates, and then clusters the extracted gradients, analyzes the resulting clusters and filters out potential bad updates before model aggregation. Extensive empirical analysis on three data sets shows the proposed defense's effectiveness against the LF attack regardless of the data distribution or model dimensionality. Also, the proposed defense outperforms several state-of-the-art defenses by offering lower test error, higher overall accuracy, higher source class accuracy, lower attack success rate, and higher stability of the source class accuracy.

Thomas Louf, Bruno Gonçalves, Jose J. Ramasco et al.

Cultural areas represent a useful concept that cross-fertilizes diverse fields in social sciences. Knowledge of how humans organize and relate their ideas and behavior within a society helps to understand their actions and attitudes towards different issues. However, the selection of common traits that shape a cultural area is somewhat arbitrary. What is needed is a method that can leverage the massive amounts of data coming online, especially through social media, to identify cultural regions without ad-hoc assumptions, biases or prejudices. This work takes a crucial step in this direction by introducing a method to infer cultural regions based on the automatic analysis of large datasets from microblogging posts. The approach presented here is based on the principle that cultural affiliation can be inferred from the topics that people discuss among themselves. Specifically, regional variations in written discourse are measured in American social media. From the frequency distributions of content words in geotagged Tweets, the regional hotspots of words' usage are found, and from there, principal components of regional variation are derived. Through a hierarchical clustering of the data in this lower-dimensional space, this method yields clear cultural areas and the topics of discussion that define them. It uncovers a manifest North-South separation, which is primarily influenced by the African American culture, and further contiguous (East-West) and non-contiguous divisions that provide a comprehensive picture of today's cultural areas in the US.

David Sánchez, Najeeb Jebreel, Krishnamurty Muralidhar et al.

The threat of reconstruction attacks has led the U.S. Census Bureau (USCB) to replace in the Decennial Census 2020 the traditional statistical disclosure limitation based on rank swapping with one based on differential privacy (DP), leading to substantial accuracy loss of released statistics. Yet, it has been argued that, if many different reconstructions are compatible with the released statistics, most of them do not correspond to actual original data, which protects against respondent reidentification. Recently, a new attack has been proposed, which incorporates the confidence that a reconstructed record was in the original data. The alleged risk of disclosure entailed by such confidence-ranked reconstruction has renewed the interest of the USCB to use DP-based solutions. To forestall a potential accuracy loss in future releases, we show that the proposed reconstruction is neither effective as a reconstruction method nor conducive to disclosure as claimed by its authors. Specifically, we report empirical results showing the proposed ranking cannot guide reidentification or attribute disclosure attacks, and hence fails to warrant the utility sacrifice entailed by the use of DP to release census statistical data.

David Sanchez, Luciano Zunino, Juan De Gregorio et al.

Words are fundamental linguistic units that connect thoughts and things through meaning. However, words do not appear independently in a text sequence. The existence of syntactic rules induces correlations among neighboring words. Using an ordinal pattern approach, we present an analysis of lexical statistical connections for 11 major languages. We find that the diverse manners that languages utilize to express word relations give rise to unique pattern structural distributions. Furthermore, fluctuations of these pattern distributions for a given language can allow us to determine both the historical period when the text was written and its author. Taken together, our results emphasize the relevance of ordinal time series analysis in linguistic typology, historical linguistics and stylometry.

Thomas Louf, José J. Ramasco, David Sánchez et al.

The socioeconomic background of people and how they use standard forms of language are not independent, as demonstrated in various sociolinguistic studies. However, the extent to which these correlations may be influenced by the mixing of people from different socioeconomic classes remains relatively unexplored from a quantitative perspective. In this work we leverage geotagged tweets and transferable computational methods to map deviations from standard English on a large scale, in seven thousand administrative areas of England and Wales. We combine these data with high-resolution income maps to assign a proxy socioeconomic indicator to home-located users. Strikingly, across eight metropolitan areas we find a consistent pattern suggesting that the more different socioeconomic classes mix, the less interdependent the frequency of their departures from standard grammar and their income become. Further, we propose an agent-based model of linguistic variety adoption that sheds light on the mechanisms that produce the observations seen in the data.

Josep Domingo-Ferrer, Najeeb Jebreel, David Sánchez

Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them. Machine unlearning has emerged as a practical means to facilitate model forgetting of data instances seen during training. Although some existing machine unlearning methods guarantee exact forgetting, they are typically costly in computational terms. On the other hand, more affordable methods do not offer forgetting guarantees and are applicable only to specific ML models. In this paper, we present \emph{efficient unlearning with privacy guarantees} (EUPG), a novel machine unlearning framework that offers formal privacy guarantees to individuals whose data are being unlearned. EUPG involves pre-training ML models on data protected using privacy models, and it enables {\em efficient unlearning with the privacy guarantees offered by the privacy models in use}. Through empirical evaluation on four heterogeneous data sets protected with $k$-anonymity and $ε$-differential privacy as privacy models, our approach demonstrates utility and forgetting effectiveness comparable to those of exact unlearning methods, while significantly reducing computational and storage costs. Our code is available at https://github.com/najeebjebreel/EUPG.

Ildikó Pilán, Pierre Lison, Lilja Øvrelid et al.

We present a novel benchmark and associated evaluation metrics for assessing the performance of text anonymization methods. Text anonymization, defined as the task of editing a text document to prevent the disclosure of personal information, currently suffers from a shortage of privacy-oriented annotated text resources, making it difficult to properly evaluate the level of privacy protection offered by various anonymization methods. This paper presents TAB (Text Anonymization Benchmark), a new, open-source annotated corpus developed to address this shortage. The corpus comprises 1,268 English-language court cases from the European Court of Human Rights (ECHR) enriched with comprehensive annotations about the personal information appearing in each document, including their semantic category, identifier type, confidential attributes, and co-reference relations. Compared to previous work, the TAB corpus is designed to go beyond traditional de-identification (which is limited to the detection of predefined semantic categories), and explicitly marks which text spans ought to be masked in order to conceal the identity of the person to be protected. Along with presenting the corpus and its annotation layers, we also propose a set of evaluation metrics that are specifically tailored towards measuring the performance of text anonymization, both in terms of privacy protection and utility preservation. We illustrate the use of the benchmark and the proposed metrics by assessing the empirical performance of several baseline text anonymization models. The full corpus along with its privacy-oriented annotation guidelines, evaluation scripts and baseline models are available on: https://github.com/NorskRegnesentral/text-anonymisation-benchmark

Juan De Gregorio, Raúl Toral, David Sánchez

Languages are grouped into families that share common linguistic traits. While this approach has been successful in understanding genetic relations between diverse languages, more analyses are needed to accurately quantify their relatedness, especially in less studied linguistic levels such as syntax. Here, we explore linguistic distances using series of parts of speech (POS) extracted from the Universal Dependencies dataset. Within an information-theoretic framework, we show that employing POS trigrams maximizes the possibility of capturing syntactic variations while being at the same time compatible with the amount of available data. Linguistic connections are then established by assessing pairwise distances based on the POS distributions. Intriguingly, our analysis reveals definite clusters that correspond to well known language families and groups, with exceptions explained by distinct morphological typologies. Furthermore, we obtain a significant correlation between language similarity and geographic distance, which underscores the influence of spatial proximity on language kinships.

Thomas Louf, David Sanchez, Jose J. Ramasco

Cultural diversity encoded within languages of the world is at risk, as many languages have become endangered in the last decades in a context of growing globalization. To preserve this diversity, it is first necessary to understand what drives language extinction, and which mechanisms might enable coexistence. Here, we study language shift mechanisms using theoretical and data-driven perspectives. A large-scale empirical analysis of multilingual societies using Twitter and census data yields a wide diversity of spatial patterns of language coexistence. It ranges from a mixing of language speakers to segregation with multilinguals on the boundaries of disjoint linguistic domains. To understand how these different states can emerge and, especially, become stable, we propose a model in which language coexistence is reached when learning the other language is facilitated and when bilinguals favor the use of the endangered language. Simulations carried out in a metapopulation framework highlight the importance of spatial interactions arising from people mobility to explain the stability of a mixed state or the presence of a boundary between two linguistic regions. Further, we find that the history of languages is critical to understand their present state.

Josep Domingo-Ferrer, David Sánchez, Alberto Blanco-Justicia

Differential privacy (DP) is a neat privacy definition that can co-exist with certain well-defined data uses in the context of interactive queries. However, DP is neither a silver bullet for all privacy problems nor a replacement for all previous privacy models. In fact, extreme care should be exercised when trying to extend its use beyond the setting it was designed for. This paper reviews the limitations of DP and its misuse for individual data collection, individual data release, and machine learning.

Bruno Gonçalves, Lucía Loureiro-Porto, José J. Ramasco et al.

As global political preeminence gradually shifted from the United Kingdom to the United States, so did the capacity to culturally influence the rest of the world. In this work, we analyze how the world-wide varieties of written English are evolving. We study both the spatial and temporal variations of vocabulary and spelling of English using a large corpus of geolocated tweets and the Google Books datasets corresponding to books published in the US and the UK. The advantage of our approach is that we can address both standard written language (Google Books) and the more colloquial forms of microblogging messages (Twitter). We find that American English is the dominant form of English outside the UK and that its influence is felt even within the UK borders. Finally, we analyze how this trend has evolved over time and the impact that some cultural events have had in shaping it.

Gonzalo Donoso, David Sanchez

In the last few years, microblogging platforms such as Twitter have given rise to a deluge of textual data that can be used for the analysis of informal communication between millions of individuals. In this work, we propose an information-theoretic approach to geographic language variation using a corpus based on Twitter. We test our models with tens of concepts and their associated keywords detected in Spanish tweets geolocated in Spain. We employ dialectometric measures (cosine similarity and Jensen-Shannon divergence) to quantify the linguistic distance on the lexical level between cells created in a uniform grid over the map. This can be done for a single concept or in the general case taking into account an average of the considered variants. The latter permits an analysis of the dialects that naturally emerge from the data. Interestingly, our results reveal the existence of two dialect macrovarieties. The first group includes a region-specific speech spoken in small towns and rural areas whereas the second cluster encompasses cities that tend to use a more uniform variety. Since the results obtained with the two different metrics qualitatively agree, our work suggests that social media corpora can be efficiently used for dialectometric analyses.

Bruno Gonçalves, David Sánchez

This paper maps the large-scale variation of the Spanish language by employing a corpus based on geographically tagged Twitter messages. Lexical dialects are extracted from an analysis of variants of tens of concepts. The resulting maps show linguistic variation on an unprecedented scale across the globe. We discuss the properties of the main dialects within a machine learning approach and find that varieties spoken in urban areas have an international character in contrast to country areas where dialects show a more regional uniformity.

Bruno Gonçalves, David Sánchez

We perform a large-scale analysis of language diatopic variation using geotagged microblogging datasets. By collecting all Twitter messages written in Spanish over more than two years, we build a corpus from which a carefully selected list of concepts allows us to characterize Spanish varieties on a global scale. A cluster analysis proves the existence of well defined macroregions sharing common lexical properties. Remarkably enough, we find that Spanish language is split into two superdialects, namely, an urban speech used across major American and Spanish citites and a diverse form that encompasses rural areas and small towns. The latter can be further clustered into smaller varieties with a stronger regional character.