相关论文: User-Level Membership Inference Attack against Met…

Recommender systems have been widely deployed across various domains such as e-commerce and social media, and intelligently suggest items like products and potential friends to users based on their preferences and interaction history, which…

Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive…

The state-of-the-art for membership inference attacks on machine learning models is a class of attacks based on shadow models that mimic the behavior of the target model on subsets of held-out nonmember data. However, we find that this…

Federated learning (FL) was originally regarded as a framework for collaborative learning among clients with data privacy protection through a coordinating server. In this paper, we propose a new active membership inference (AMI) attack…

Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…

Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requires huge amounts of data that might contain…

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…

A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In…

It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. Applying mixup in training provides an effective mechanism to…

Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues. Membership Inference Attacks (MIAs) are designed to ascertain whether specific data was…

Model Inversion (MI) attacks aim to recover the private training data from the target model, which has raised security concerns about the deployment of DNNs in practice. Recent advances in generative adversarial models have rendered them…

With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and robotic control.…

Membership inference attacks are used as a key tool for disclosure auditing. They aim to infer whether an individual record was used to train a model. While such evaluations are useful to demonstrate risk, they are computationally expensive…

Many real-world data comes in the form of graphs, such as social networks and protein structure. To fully utilize the information contained in graph data, a new family of machine learning (ML) models, namely graph neural networks (GNNs),…

Graph embeddings have been proposed to map graph data to low dimensional space for downstream processing (e.g., node classification or link prediction). With the increasing collection of personal data, graph embeddings can be trained on…

Generative models can unintentionally memorize training data, posing significant privacy risks. This paper addresses the memorization phenomenon in time series imputation models, introducing the Loss-Based with Reference Model (LBRM)…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

We consider the problem of a training data proof, where a data creator or owner wants to demonstrate to a third party that some machine learning model was trained on their data. Training data proofs play a key role in recent lawsuits…

Membership inference attacks (MIAs) aim to determine whether a specific data point was part of a model's training set, serving as effective tools for evaluating privacy leakage of vision models. However, existing MIAs implicitly assume…

With the widespread adoption of Large Language Models (LLMs) and increasingly stringent privacy regulations, protecting data privacy in LLMs has become essential, especially for privacy-sensitive applications. Membership Inference Attacks…