相关论文: Generative Model Inversion Through the Lens of the…

Reliable training of generative adversarial networks (GANs) typically require massive datasets in order to model complicated distributions. However, in several applications, training samples obey invariances that are \textit{a priori}…

Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model diagnosis). In particular, the gradient-based trigger…

Membership inference attacks (MIAs) aim to determine whether specific data were used to train a model. While extensively studied on classification models, their impact on time series forecasting remains largely unexplored. We address this…

Model-based attacks can infer training data information from deep neural network models. These attacks heavily depend on the attacker's knowledge of the application domain, e.g., using it to determine the auxiliary data for model-inversion…

Machine-learning (ML) algorithms or models, especially deep neural networks (DNNs), have shown significant promise in several areas. However, researchers have recently demonstrated that ML algorithms, especially DNNs, are vulnerable to…

Generative models are popular tools with a wide range of applications. Nevertheless, it is as vulnerable to adversarial samples as classifiers. The existing attack methods mainly focus on generating adversarial examples by adding…

Deep learning models, while achieving remarkable performances, are vulnerable to membership inference attacks (MIAs). Although various defenses have been proposed, there is still substantial room for improvement in the privacy-utility…

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently. Most of these methods use a shared discriminator/classifier which discriminates real examples from fake while…

With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in…

Generative networks are fundamentally different in their aim and methods compared to CNNs for classification, segmentation, or object detection. They have initially not been meant to be an image analysis tool, but to produce naturally…

We study the privacy implications of training recurrent neural networks (RNNs) with sensitive training datasets. Considering membership inference attacks (MIAs), which aim to infer whether or not specific data records have been used in…

Generative methods (Gen-AI) are reviewed with a particular goal of solving tasks in machine learning and Bayesian inference. Generative models require one to simulate a large training dataset and to use deep neural networks to solve a…

Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is…

One of the main motivations for training high quality image generative models is their potential use as tools for image manipulation. Recently, generative adversarial networks (GANs) have been able to generate images of remarkable quality.…

ViTs are often too computationally expensive to be fitted onto real-world resource-constrained devices, due to (1) their quadratically increased complexity with the number of input tokens and (2) their overparameterized self-attention heads…

Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While…

Gradient inversion attacks are often presented as a serious privacy threat in federated learning, with recent work reporting increasingly strong reconstructions under favorable experimental settings. However, it remains unclear whether such…

Seismic inverse modeling is a common method in reservoir prediction and it plays a vital role in the exploration and development of oil and gas. Conventional seismic inversion method is difficult to combine with complicated and abstract…

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…