相关论文: M^4I: Multi-modal Models Membership Inference

Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios. However, their emergence also raises significant data security concerns, given the potential…

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…

With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model developers may misuse the unauthorized data to train…

In a membership inference attack, an attacker aims to infer whether a data sample is in a target classifier's training dataset or not. Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier,…

With the development of information science and technology, various industries have generated massive amounts of data, and machine learning is widely used in the analysis of big data. However, if the privacy of machine learning…

Membership inference attacks (MIAs) reveal whether specific data was used to train machine learning models, serving as important tools for privacy auditing and compliance assessment. Recent studies have reported that MIAs perform only…

Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressing question. Membership inference attacks are the standard…

Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary…

Differentially private models seek to protect the privacy of data the model is trained on, making it an important component of model security and privacy. At the same time, data scientists and machine learning engineers seek to use…

Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task.…

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…

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the…

A Membership Inference Attack (MIA) assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or…

While significant research advances have been made in the field of deep reinforcement learning, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning…

Membership Inference Attack (MIA) aims to determine whether a specific data sample was included in the training dataset of a target model. Traditional MIA approaches rely on shadow models to mimic target model behavior, but their…

With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-quality pre-trained image-generative models, a growing number…

Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. Despite extensive research on traditional machine learning models, there has been limited work studying MIA…

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…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

Model-sharing offers significant business value by enabling firms with well-established Machine Learning (ML) models to monetize and share their models with others who lack the resources to develop ML models from scratch. However, concerns…