相关论文: On the Privacy Risks of Deploying Recurrent Neural…

Spiking Neural Networks (SNNs) are increasingly explored for their energy efficiency and robustness in real-world applications, yet their privacy risks remain largely unexamined. In this work, we investigate the susceptibility of SNNs to…

As machine learning models increasingly process sensitive data, understanding their vulnerability to privacy attacks is vital. Membership inference attacks (MIAs) exploit model responses to infer whether specific data points were used…

Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…

In several jurisdictions, the regulatory framework on the release and sharing of personal data is being extended to machine learning (ML). The implicit assumption is that disclosing a trained ML model entails a privacy risk for any personal…

Artificial Neural Networks (ANNs), commonly mimicking neurons with non-linear functions to output floating-point numbers, consistently receive the same signals of a data point during its forward time. Unlike ANNs, Spiking Neural Networks…

Deep learning models often raise privacy concerns as they leak information about their training data. This enables an adversary to determine whether a data point was in a model's training set by conducting a membership inference attack…

Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a specific data sample was included in the training set. Although federated learning (FL) is…

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training. In this paper, we propose a novel and effective Neuron-Guided Defense method named…

Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…

Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…

While machine learning (ML) models are becoming mainstream, especially in sensitive application areas, the risk of data leakage has become a growing concern. Attacks like membership inference (MIA) have shown that trained models can reveal…

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…

The success of deep neural networks has driven numerous research studies and applications from Euclidean to non-Euclidean data. However, there are increasing concerns about privacy leakage, as these networks rely on processing private data.…

An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…

Multi-domain graph pre-training has emerged as a pivotal technique in developing graph foundation models. While it greatly improves the generalization of graph neural networks, its privacy risks under membership inference attacks (MIAs),…

Training a machine learning model with data following a meaningful order, i.e., from easy to hard, has been proven to be effective in accelerating the training process and achieving better model performance. The key enabling technique is…

Differential privacy (DP) is a gold-standard concept of measuring and guaranteeing privacy in data analysis. It is well-known that the cost of adding DP to deep learning model is its accuracy. However, it remains unclear how it affects…

While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). This paper presents an empirical evaluation of Differential Privacy (DP) as a defense…