相关论文: PATROL: Privacy-Oriented Pruning for Collaborative…

The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitting. Overfitted models have been shown to be susceptible to…

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in…

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research reveals that backdoors can be erased from infected DNNs by pruning a specific group of…

Graph Prompt Learning (GPL) represents an innovative approach in graph representation learning, enabling task-specific adaptations by fine-tuning prompts without altering the underlying pre-trained model. Despite its growing prominence, the…

With the rise of large language models, service providers offer language models as a service, enabling users to fine-tune customized models via uploaded private datasets. However, this raises concerns about sensitive data leakage. Prior…

Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…

Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks,…

Deep neural networks (DNNs) are increasingly used in critical applications such as identity authentication and autonomous driving, where robustness against adversarial attacks is crucial. These attacks can exploit minor perturbations to…

Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality during training processes does not provide sufficient privacy…

Spatiotemporal federated learning has recently raised intensive studies due to its ability to train valuable models with only shared gradients in various location-based services. On the other hand, recent studies have shown that shared…

The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory measures like GDPR and CCPA call for using robust auditing…

As machine learning (ML) technologies become more prevalent in privacy-sensitive areas like healthcare and finance, eventually incorporating sensitive information in building data-driven algorithms, it is vital to scrutinize whether these…

Differential Privacy (DP) is widely adopted in data management systems to enable data sharing with formal disclosure guarantees. A central systems challenge is understanding how DP noise translates into effective protection against…

Approximate machine unlearning aims to remove the effect of specific data from trained models to ensure individuals' privacy. Existing methods focus on the removed records and assume the retained ones are unaffected. However, recent studies…

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to…

Utilization of Machine Learning (ML) algorithms, especially Deep Neural Network (DNN) models, becomes a widely accepted standard in many domains more particularly IoT-based systems. DNN models reach impressive performances in several…

Membership Inference Attacks (MIAs) have emerged as a principled framework for auditing the privacy of synthetic data generated by tabular generative models, where many diverse methods have been proposed that each exploit different privacy…

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

Training deep neural networks often forces users to work in a distributed or outsourced setting, accompanied with privacy concerns. Split learning aims to address this concern by distributing the model among a client and a server. The…

Federated Learning (FL) enables collaborative model training while keeping training data localized, allowing us to preserve privacy in various domains including remote sensing. However, recent studies show that FL models may still leak…