Sensitive Attributes Research Articles

FairGap: Fairness-Aware Recommendation via Generating Counterfactual Graph

The emergence of Graph Neural Networks (GNNs) has greatly advanced the development of recommendation systems. Recently, many researchers have leveraged GNN-based models to learn fair representations for users and items. However, current GNN-based models suffer from biased user–item interaction data, which negatively impacts recommendation fairness. Although there have been several studies employing adversarial learning to mitigate this issue in recommendation systems, they mostly focus on modifying the model training approach with fairness regularization and neglect direct intervention of biased interaction. In contrast to these models, this article introduces a novel perspective by directly intervening in observed interactions to generate a counterfactual graph (called FairGap) that is not influenced by sensitive node attributes, enabling us to learn fair representations for users and items easily. We design FairGap to answer the key counterfactual question: “Would interactions with an item remain unchanged if a user’s sensitive attributes were concealed?”. We also provide theoretical proofs to show that our learning strategy via the counterfactual graph is unbiased in expectation. Moreover, we propose a fairness-enhancing mechanism to continuously improve user fairness in the graph-based recommendation. Extensive experimental results against state-of-the-art competitors and base models on three real-world datasets validate the effectiveness of our proposed model.

Learning Fair Representations via Distance Correlation Minimization.

As machine learning algorithms are increasingly deployed for high-impact automated decision-making, the presence of bias (in datasets or tasks) gradually becomes one of the most critical challenges in machine learning applications. Such challenges range from the bias of race in face recognition to the bias of gender in hiring systems, where race and gender can be denoted as sensitive attributes. In recent years, much progress has been made in ensuring fairness and reducing bias in standard machine learning settings. Among them, learning fair representations with respect to the sensitive attributes has attracted increasing attention due to its flexibility in learning the rich representations based on advances in deep learning. In this article, we propose graph-fair, an algorithmic approach to learning fair representations under the graph Laplacian regularization, which reduces the separation between groups and the clustering within a group by encoding the sensitive attribute information into the graph. We have theoretically proved the underlying connection between graph regularization and distance correlation and show that the latter can be regarded as a standardized version of the former, with an additional advantage of being scale-invariant. Therefore, we naturally adopt the distance correlation as the fairness constraint to decrease the dependence between sensitive attributes and latent representations, called dist-fair. In contrast to existing approaches using measures of dependency and adversarial generators, both graph-fair and dist-fair provide simple fairness constraints, which eliminate the need for parameter tuning (e.g., choosing kernels) and introducing adversarial networks. Experiments conducted on real-world corpora indicate that our proposed fairness constraints applied for representation learning can provide better tradeoffs between fairness and utility results than existing approaches.

Evaluasi Keberlanjutan Usahatani Sayuran Dalam Sistem Agroforestry Di Daerah Aliran Sungai (DAS) Brantas Hulu, Jawa Timur, Indonesia Dengan Metode Multi Dimensional Scaling (MDS)

<p>Sustainable agricultural system is an agricultural system that is ecologically viable (environmentally friendly), economically viable and socially acceptable and does not conflict with the culture of the local community. The Upper Brantas River Basin (DAS) is one of the most strategic areas in East Java Province, Indoensia, because of its function as an area for providing raw water and producing environmental services. However, as time goes by, population growth in the area continues to increase, this can causing high pressure on land use for settlements, increasingly intensive agriculture, even on land with a slope of more than 30 degrees. One way to overcome this problem is by implementing agroforestry. The aim of this research is to evaluate the sustainability of vegetable farming using an agroforestry system from ecological, economic and socio-cultural dimensions in the Upper Brantas Watershed Area, as well as analyzing sensitive attributes that influence sustainability status. The number of respondents in this research is 60 which consist of farmers who have selected randomly, key informan and stakeholders. The data analysis method used is Multidimensional Scaling (MDS) through the Rap-farm coordination technique. The results of the research show that vegetable farming in the Upper Brantas watershed in the agroforestry system has a sustainability status that is in the 'moderately sustainable' category with an index score in the ecological dimensions of 76.30 (very sustainable), economic of 54.83 (quite sustainable) and social culture of 63.06 (quite sustainable). Sensitive attributes in the ecological dimension are waste recycling and livestock ownership, the economic dimension is land ownership and marketing of agricultural products, and the socio-cultural dimension is the health level of farming households.</p>

Causality-Based Fair Multiple Decision by Response Functions

A recent trend of fair machine learning is to build a decision model subjected to causality-based fairness requirements, which concern with the causality between sensitive attributes and decisions. Almost all (if not all) solutions focus on a single fair decision model and assume no hidden confounder to model causal effects in a too simplified way. However, multiple interdependent decision models are actually used and discrimination may transmit among them. The hidden confounder is another inescapable fact and causal effects cannot be computed from observational data in the unidentifiable situation. To address these problems, we propose a method called CMFL (Causality-based Multiple Fairness Learning). CMFL parameterizes the causal model by response-function variables, whose distributions capture the randomness of causal models. CMFL treats each classifier as a soft intervention to infer the post-intervention distribution, and combines the fairness constraints with the classification loss to train multiple decision classifiers. In this way, all classifiers can make approximately fair decisions. Experiments on synthetic and benchmark datasets confirm its effectiveness, the response-function variables can deal with the unidentifiable issue and hidden confounders.

Adaptive Personalized Randomized Response Method Based on Local Differential Privacy

Aiming at the problem of adopting the same level of privacy protection for sensitive data in the process of data collection and ignoring the difference in privacy protection requirements, the authors propose an adaptive personalized randomized response method based on local differential privacy (LDP-APRR). LDP-APRR determines the sensitive level through the user scoring strategy, introduces the concept of sensitive weights for adaptive allocation of privacy budget, and realizes the personalized privacy protection of sensitive attributes and attribute values. To verify the distorted data availability, LDP-APRR is applied to frequent items mining scenarios and compared with mining associations with secrecy konstraints (MASK), and grouping-based randomization for privacy-preserving frequent pattern mining (GR-PPFM). Results show that the LDP-APRR achieves personalized protection of sensitive attributes and attribute values with user participation, and the maxPrivacy and avgPrivacy are improved by 1.2% and 4.3%, respectively, while the availability of distorted data is guaranteed.

A Probability Proportional to Size Estimation of a Rare Sensitive Attribute Using a Partial Randomized Response Model with Poisson Distribution

In this paper, we suggest using a partial randomized response model using Poisson distribution to efficiently estimate a rare sensitive attribute by applying the probability proportional to size (PPS) sampling method when the population is composed of several different and sensitive clusters. We have obtained estimators for a rare and sensitive attribute and their variances and variance estimates by applying PPS sampling and two-stage equal probability sampling. We compare the efficiency between the estimators of the rare sensitive attribute, one obtained via PPS sampling with replacement and the other obtained using the two-stage equal probability sampling with replacement. As a result, it is confirmed that the estimate obtained via the PPS sampling with replacement is more efficient than the estimate provided by the two-stage equal probability sampling with replacement when the cluster sizes are different.

Voice Fence Wall: User-optional voice privacy transmission

Sensors are widely applied in the collection of voice data. Since many attributes of voice data are sensitive such as user emotions, identity, raw voice collection may lead serious privacy threat. In the past, traditional feature extraction obtains and encrypts voice features that are then transmitted to upstream servers. In order to avoid sensitive attribute disclosure, it is necessary to separate the sensitive attributes from non-sensitive attributes of voice data. Motivated by this, user-optional privacy transmission framework for voice data (called: Voice Fence Wall) is proposed. Firstly, we provide user-optional, which means users can choose the attributes (sensitive attributes) they want to be protected. Secondly, Voice Fence Wall utilizes minimum mutual information (MI) to reduce the correlation between sensitive and non-sensitive attributes, thereby separating these attributes. Finally, only the separated non-sensitive attributes are transmitted to the upstream server, the quality of voice services is satisfied without leaking sensitive attributes. To verify the reliability and practicability, three voice datasets are used to evaluate the model, the experiments demonstrate that Voice Fence Wall not only effectively separates attributes to resist attribute inference attacks, but also outperforms related work in terms of classification performance. Specifically, our framework achieves 89.84 ​% accuracy in sentiment recognition and 6.01 ​% equal error rate in voice authentication.

Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithms

Fairness in machine learning (ML) is an ever-growing field of research due to the manifold potential for harm from algorithmic discrimination. To prevent such harm, a large body of literature develops new approaches to quantify fairness. Here, we investigate how one can divert the quantification of fairness by describing a practice we call “fairness hacking” for the purpose of shrouding unfairness in algorithms. This impacts end-users who rely on learning algorithms, as well as the broader community interested in fair AI practices. We introduce two different categories of fairness hacking in reference to the established concept of p-hacking. The first category, intra-metric fairness hacking, describes the misuse of a particular metric by adding or removing sensitive attributes from the analysis. In this context, countermeasures that have been developed to prevent or reduce p-hacking can be applied to similarly prevent or reduce fairness hacking. The second category of fairness hacking is inter-metric fairness hacking. Inter-metric fairness hacking is the search for a specific fair metric with given attributes. We argue that countermeasures to prevent or reduce inter-metric fairness hacking are still in their infancy. Finally, we demonstrate both types of fairness hacking using real datasets. Our paper intends to serve as a guidance for discussions within the fair ML community to prevent or reduce the misuse of fairness metrics, and thus reduce overall harm from ML applications.

Search-based Automatic Repair for Fairness and Accuracy in Decision-making Software

Decision-making software mainly based on Machine Learning (ML) may contain fairness issues (e.g., providing favourable treatment to certain people rather than others based on sensitive attributes such as gender or race). Various mitigation methods have been proposed to automatically repair fairness issues to achieve fairer ML software and help software engineers to create responsible software. However, existing bias mitigation methods trade accuracy for fairness (i.e., trade a reduction in accuracy for better fairness). In this paper, we present a novel search-based method for repairing ML-based decision making software to simultaneously increase both its fairness and accuracy. As far as we know, this is the first bias mitigation approach based on multi-objective search that aims to repair fairness issues without trading accuracy for binary classification methods. We apply our approach to two widely studied ML models in the software fairness literature (i.e., Logistic Regression and Decision Trees), and compare it with seven publicly available state-of-the-art bias mitigation methods by using three different fairness measurements. The results show that our approach successfully increases both accuracy and fairness for 61% of the cases studied, while the state-of-the-art always decrease accuracy when attempting to reduce bias. With our proposed approach, software engineers that previously were concerned with accuracy losses when considering fairness, are now enabled to improve the fairness of binary classification models without sacrificing accuracy.

Differentially Private and Fair Machine Learning: A Benchmark Study

With the increasing adoption of machine learning systems, concerns around bias and privacy have gained significant research interest. This work investigates the intersection of algorithmic fairness and differential privacy by evaluating differentially private fair representations. The LAFTR framework aims to learn fair data representations while maintaining utility. Differential privacy is injected into model training using DP-SGD to provide formal privacy guarantees. Experiments are conducted on the Adult, German Credit, and CelebA datasets, with gender and age as sensitive attributes. The models are evaluated across various configurations, including the privacy budget epsilon, adversary strength, and dataset characteristics. Results demonstrate that with proper tuning, differentially private models can achieve fair representations comparable or better than non-private models. However, introducing privacy reduces stability during training. Overall, the analysis provides insights into the tradeoffs between accuracy, fairness and privacy for different model configurations across datasets. The results establish a benchmark for further research into differentially private and fair machine learning models, advancing the understanding of training under an adversary.

CRISPR/Cas12a antifouling nanocomposite electrochemical biosensors enable amplification-free detection of Monkeypox virus in complex biological fluids.

The escalating global threat of infectious diseases, including monkeypox virus (MPXV), necessitates advancements in point-of-care diagnostics, moving beyond the constraints of conventional methods tethered to centralized laboratories. Here, we introduce multiple CRISPR RNA (crRNA)-based biosensors that can directly detect MPXV within 35 minutes without pre-amplification, leveraging the enhanced sensitivity and antifouling attributes of the BSA-based nanocomposite. Multiple crRNAs, strategically targeting diverse regions of the F3L gene of MPXV, are designed and combined to amplify Cas12a activation and its collateral cleavage of reporter probes. Notably, our electrochemical sensors exhibit the detection limit of 669 fM F3L gene without amplification, which is approximately a 15-fold improvement compared to fluorescence detection. This sensor also shows negligible changes in peak current after exposure to complex biological fluids, such as whole blood and serum, maintaining its sensitivity at 682 fM. This sensitivity is nearly identical to the conditions when only the F3L gene was present in PBS. In summary, our CRISPR-based electrochemical biosensors can be utilized as a high-performance diagnostic tool in resource-limited settings, representing a transformative leap forward in point-of-care testing. Beyond infectious diseases, the implications of this technology extend to various molecular diagnostics, establishing itself as a rapid, accurate, and versatile platform for detection of target analytes.

Privacy Protection of Multiple Sensitive Attribute Data for Users on E-commerce Social Media Platforms

Privacy Protection of Multiple Sensitive Attribute Data for Users on E-commerce Social Media Platforms

LDCML: A Novel AI-Driven Approach form Privacy-Preserving Anonymization of Quasi-Identifiers

Introduction: the exponential growth of data generation has led to an escalating concern for data privacy on a global scale. This work introduces a pioneering approach to address the often overlooked data privacy leakages associated with quasi-identifiers, leveraging artificial intelligence, machine learning and data correlation analysis as foundational tools. Traditional data privacy measures predominantly focus on anonymizing sensitive attributes and exact identifiers, leaving quasi-identifiers in their raw form, potentially exposing privacy vulnerabilities.Objective: the primary objective of the presented work, is to anonymise the quasi-identifiers to enhance the overall data privacy preservation with minimal data utility degradation.Methods: In this study, the authors propose the integration of ℓ-diversity data privacy algorithms with the OPTICS clustering technique and data correlation analysis to anonymize the quasi-identifiers.Results: to assess its efficacy, the proposed approach is rigorously compared against benchmark algorithms. The datasets used are - Adult dataset and Heart Disease Dataset from the UCI machine learning repository. The comparative metrics are - Relative Distance, Information Loss, KL Divergence and Execution Time.Conclusion: the comparative performance evaluation of the proposed methodology demonstrates its superiority over established benchmark techniques, positioning it as a promising solution for the requisite data privacy-preserving model. Moreover, this analysis underscores the imperative of integrating artificial intelligence (AI) methodologies into data privacy paradigms, emphasizing the necessity of such approaches in contemporary research and application domains

Practical Attribute Reconstruction Attack Against Federated Learning

Existing federated learning (FL) designs have been shown to exhibit vulnerabilities which can be exploited by adversaries to compromise data privacy. However, most current works conduct attacks by leveraging gradients calculated on a small batch of data. This setting is not realistic as gradients are normally shared after at least 1 epoch of local training on each participant's local data in FL for communication efficiency. In this work, we conduct a unique systematic evaluation of attribute reconstruction attack (ARA) launched by the malicious server in the FL system, and empirically demonstrate that the shared local model gradients after 1 epoch of local training can still reveal sensitive attributes of local training data. To demonstrate this leakage, we develop a more effective and efficient gradient matching based method called cos-matching to reconstruct the sensitive attributes of any victim participant's training data. Based on the reconstructed training data attributes, we further show that an attacker can even reconstruct the sensitive attributes of any records that are not included in any participant's training data, thus opening a new attack surface in FL. Extensive experiments show that the proposed method achieves better attribute attack performance than existing state-of-the-art methods.

MultiFair: Model Fairness With Multiple Sensitive Attributes.

While existing fairness interventions show promise in mitigating biased predictions, most studies concentrate on single-attribute protections. Although a few methods consider multiple attributes, they either require additional constraints or prediction heads, incurring high computational overhead or jeopardizing the stability of the training process. More critically, they consider per-attribute protection approaches, raising concerns about fairness gerrymandering where certain attribute combinations remain unfair. This work aims to construct a neutral domain containing fused information across all subgroups and attributes. It delivers fair predictions as the fused input contains neutralized information for all considered attributes. Specifically, we adopt mixup operations to generate samples with fused information. However, our experiments reveal that directly adopting the operations leads to degraded prediction results. The excessive mixup operations result in unrecognizable training data. To this end, we design three distinct mixup schemes that balance information fusion across attributes while retaining distinct visual features critical for training valid models. Extensive experiments with multiple datasets and up to eight sensitive attributes demonstrate that the proposed MultiFair method can deliver fairness protections for multiple attributes while maintaining valid prediction results.

Fertilidade e estoque de carbono em ambientes de pastagem e floresta no sul da Amazônia

ABSTRACT Inadequate management of pasture soils in the Amazon has resulted in a predominance of degraded pastures. Considering the natural characteristics of this region can favor more appropriate strategies for sustainability, the objective of this study was to evaluate the differences in the chemical and physical attributes of pasture and forest soils in the Southern Amazon and to identify the most sensitive attributes of their fertility. Additionally, this study suggests appropriate management practices for sustainable pastures. Soil samples from the 0 to 0.20 m layer were analyzed to determine pH, exchangeable bases (calcium, magnesium, and potassium), exchangeable aluminum, potential acidity, phosphorus, organic carbon, bulk density, and texture. Pasture soils had a higher pH, calcium content, and bulk density than forest soils. However, the pasture soils had lower phosphorus and organic matter content. The soil organic carbon stocks were also lower in pasture soils, with levels 0.8 to 12 Mg ha-1 lower than in forest soils. The fertility attributes most sensitive to soil management in these pastures were phosphorus, pH, organic carbon, and bulk density. The lack of nutrients and soil and water conservation practices have contributed to the degradation of these pastures. Therefore, the recommended management for these pastures should aim to improve the organic matter content, reduce compaction, and replenish and cycle nutrients.

Skin-Inspired, Highly Sensitive, Broad-Range-Response and Ultra-Strong Gradient Ionogels Prepared by Electron Beam Irradiation.

Skin, characterized by its distinctive gradient structure and interwoven fibers, possesses remarkable mechanical properties and highly sensitive attributes, enabling it to detect an extensive range of stimuli. Inspired by these inherent qualities, a pioneering approach involving the crosslinking of macromolecules through in situ electron beam irradiation (EBI) is proposed to fabricate gradient ionogels. Such a design offers remarkable mechanical properties, including excellent tensile properties (>1000%), exceptional toughness (100MJ m-3), fatigue resistance, a broad temperature range (-65-200°C), and a distinctive gradient modulus change. Moreover, the ionogel sensor exhibits an ultra-fast response time (60ms) comparable to skin, an incredibly low detection limit (1kPa), and an exceptionally wide detection range (1kPa-1MPa). The exceptional gradient ionogel material holds tremendous promise for applications in the field of smart sensors, presenting a distinct strategy for fabricating flexible gradient materials.

F3KM: Federated, Fair, and Fast k-means

This paper proposes a federated, fair, and fast k-means algorithm (F3KM) to solve the fair clustering problem efficiently in scenarios where data cannot be shared among different parties. The proposed algorithm decomposes the fair k-means problem into multiple subproblems and assigns each subproblem to a client for local computation. Our algorithm allows each client to possess multiple sensitive attributes (or have no sensitive attributes). We propose an in-processing method that employs the alternating direction method of multipliers (ADMM) to solve each subproblem. During the procedure of solving subproblems, only the computation results are exchanged between the server and the clients, without exchanging the raw data. Our theoretical analysis shows that F3KM is efficient in terms of both communication and computation complexities. Specifically, it achieves a better trade-off between utility and communication complexity, and reduces the computation complexity to linear with respect to the dataset size. Our experiments show that F3KM achieves a better trade-off between utility and fairness than other methods. Moreover, F3KM is able to cluster five million points in one hour, highlighting its impressive efficiency.

Learning Dynamic Prototypes for Visual Pattern Debiasing

AbstractDeep learning has achieved great success in academic benchmarks but fails to work effectively in the real world due to the potential dataset bias. The current learning methods are prone to inheriting or even amplifying the bias present in a training dataset and under-represent specific demographic groups. More recently, some dataset debiasing methods have been developed to address the above challenges based on the awareness of protected or sensitive attribute labels. However, the number of protected or sensitive attributes may be considerably large, making it laborious and costly to acquire sufficient manual annotation. To this end, we propose a prototype-based network to dynamically balance the learning of different subgroups for a given dataset. First, an object pattern embedding mechanism is presented to make the network focus on the foreground region. Then we design a prototype learning method to discover and extract the visual patterns from the training data in an unsupervised way. The number of prototypes is dynamic depending on the pattern structure of the feature space. We evaluate the proposed prototype-based network on three widely used polyp segmentation datasets with abundant qualitative and quantitative experiments. Experimental results show that our proposed method outperforms the CNN-based and transformer-based state-of-the-art methods in terms of both effectiveness and fairness metrics. Moreover, extensive ablation studies are conducted to show the effectiveness of each proposed component and various parameter values. Lastly, we analyze how the number of prototypes grows during the training process and visualize the associated subgroups for each learned prototype. The code and data will be released at https://github.com/zijinY/dynamic-prototype-debiasing.

FAL-CUR: Fair Active Learning using Uncertainty and Representativeness on Fair Clustering

Active Learning (AL) techniques have proven to be highly effective in reducing data labeling costs across a range of machine learning tasks. Nevertheless, one known challenge of these methods is their potential to introduce unfairness towards sensitive attributes. Although recent approaches have focused on enhancing fairness in AL, they tend to reduce the model’s accuracy. To address this issue, we propose a novel strategy, named Fair Active Learning using fair Clustering, Uncertainty, and Representativeness (FAL-CUR), to improve fairness in AL. FAL-CUR tackles the fairness problem in AL by combining fair clustering with an acquisition function that determines which samples to query based on their uncertainty and representativeness scores. We evaluate the performance of FAL-CUR on four real-world datasets, and the results demonstrate that FAL-CUR achieves a 15%–20% improvement in fairness compared to the best state-of-the-art method in terms of equalized odds while maintaining stable accuracy scores. Furthermore, an ablation study highlights the crucial roles of fair clustering in preserving fairness and the acquisition function in stabilizing the accuracy performance.