相关论文: Quantifying the Privacy Implications of High-Fidel…

Recent advancements in generative AI have made it possible to create synthetic datasets that can be as accurate as real-world data for training AI models, powering statistical insights, and fostering collaboration with sensitive datasets…

Tabular Generative Models are often argued to preserve privacy by creating synthetic datasets that resemble training data. However, auditing their empirical privacy remains challenging, as commonly used similarity metrics fail to…

Auditing the privacy leakage of synthetic data is an important but unresolved problem. Existing privacy auditing frameworks for synthetic data rely on heuristics and unrealistic assumptions about model access, offering limited ability to…

How much information about training samples can be leaked through synthetic data generated by Large Language Models (LLMs)? Overlooking the subtleties of information flow in synthetic data generation pipelines can lead to a false sense of…

Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitating the sharing of sensitive data. However, it is crucial to…

The availability of genomic data is essential to progress in biomedical research, personalized medicine, etc. However, its extreme sensitivity makes it problematic, if not outright impossible, to publish or share it. As a result, several…

When acting as a privacy-enhancing technology, synthetic data generation (SDG) aims to maintain a resemblance to the real data while excluding personally-identifiable information. Many SDG algorithms provide robust differential privacy (DP)…

Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despite extensive research on MIAs, systematic comparisons between…

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…

Generative models are increasingly used to produce privacy-preserving synthetic data as a safe alternative to sharing sensitive training datasets. However, we demonstrate that such synthetic releases can still leak information about the…

Smart vehicles produce large amounts of data, much of which is sensitive and at risk of privacy breaches. As attackers increasingly exploit anonymised metadata within these datasets to profile drivers, it's important to find solutions that…

Synthetic data has become an increasingly popular way to share data without revealing sensitive information. Though Membership Inference Attacks (MIAs) are widely considered the gold standard for empirically assessing the privacy of a…

Generative models producing synthetic data are meant to provide a privacy-friendly approach to releasing data. However, their privacy guarantees are only considered robust when models satisfy Differential Privacy (DP). Alas, this is not a…

Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a potential solution. It aims to generate data that…

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…

Synthetic data generation (SDG) has become increasingly popular as a privacy-enhancing technology. It aims to maintain important statistical properties of its underlying training data, while excluding any personally identifiable…

Synthetic data is emerging as one of the most promising solutions to share individual-level data while safeguarding privacy. While membership inference attacks (MIAs), based on shadow modeling, have become the standard to evaluate the…

Privacy attacks, particularly membership inference attacks (MIAs), are widely used to assess the privacy of generative models for tabular synthetic data, including those with Differential Privacy (DP) guarantees. These attacks often exploit…

Training generative machine learning models to produce synthetic tabular data has become a popular approach for enhancing privacy in data sharing. As this typically involves processing sensitive personal information, releasing either the…

Artificial intelligence and machine learning have been integrated into all aspects of our lives and the privacy of personal data has attracted more and more attention. Since the generation of the model needs to extract the effective…