相关论文: Do Fairness Interventions Come at the Cost of Priv…

Algorithmic fairness has attracted significant attention in recent years, with many quantitative measures suggested for characterizing the fairness of different machine learning algorithms. Despite this interest, the robustness of those…

The integration of AI in education holds immense potential for personalizing learning experiences and transforming instructional practices. However, AI systems can inadvertently encode and amplify biases present in educational data, leading…

This report summarizes all the MIA experiments (Membership Inference Attacks) of the Embedding Attack Project, including threat models, experimental setup, experimental results, findings and discussion. Current results cover the evaluation…

Privacy and algorithmic fairness have become two central issues in modern machine learning. Although each has separately emerged as a rapidly growing research area, their joint effect remains comparatively under-explored. In this paper, we…

We investigate the fairness concerns of training a machine learning model using data with missing values. Even though there are a number of fairness intervention methods in the literature, most of them require a complete training set as…

Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model. Prior work has shown that the attack is feasible when the model is overfitted to its training data or…

Trustworthy AI encompasses many aspirational aspects for aligning AI systems with human values, including fairness, privacy, robustness, explainability, and uncertainty quantification. Ultimately the goal of Trustworthy AI research is to…

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privacy (DP) to protect sensitive data, their sensitivity to…

As Machine Learning technologies become increasingly used in contexts that affect citizens, companies as well as researchers need to be confident that their application of these methods will not have unexpected social implications, such as…

Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box access to the model parameters increases the attack surface…

Artificial Intelligence (AI) has attracted a great deal of attention in recent years. However, alongside all its advancements, problems have also emerged, such as privacy violations, security issues and model fairness. Differential privacy,…

Ensuring trustworthiness in machine learning (ML) models is a multi-dimensional task. In addition to the traditional notion of predictive performance, other notions such as privacy, fairness, robustness to distribution shift, adversarial…

Membership inference attacks (MIAs) on diffusion models have emerged as potential evidence of unauthorized data usage in training pre-trained diffusion models. These attacks aim to detect the presence of specific images in training datasets…

The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their premises and without relying on any central entity. However,…

Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier's vulnerability to membership inference attacks. We first demonstrate how the number of parameters of a model…

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms…

Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…

The performance cost of differential privacy has, for some applications, been shown to be higher for minority groups; fairness, conversely, has been shown to disproportionally compromise the privacy of members of such groups. Most work in…

As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e.g., gender and racial biases) has come to the fore of the public's…

Membership inference attacks (MIAs) are widely used to empirically assess privacy risks in machine learning models, both providing model-level vulnerability metrics and identifying the most vulnerable training samples. State-of-the-art…