相关论文: Measuring pattern retention in anonymized data -- …

Composition is a key feature of differential privacy. Well-known advanced composition theorems allow one to query a private database quadratically more times than basic privacy composition would permit. However, these results require that…

Today, computer systems hold large amounts of personal data. Yet while such an abundance of data allows breakthroughs in artificial intelligence, and especially machine learning (ML), its existence can be a threat to user privacy, and it…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

Updating machine learning models with new information usually improves their predictive performance, yet, in many applications, it is also desirable to avoid changing the model predictions too much. This property is called stability. In…

We study the problem of data release with privacy, where data is made available with privacy guarantees while keeping the usability of the data as high as possible --- this is important in health-care and other domains with sensitive data.…

Camouflaging data by generating fake information is a well-known obfuscation technique for protecting data privacy. In this paper, we focus on a very sensitive and increasingly exposed type of data: location data. There are two main…

Optimization of human-AI teams hinges on the AI's ability to tailor its interaction to individual human teammates. A common hypothesis in adaptive AI research is that minor differences in people's predisposition to trust can significantly…

To prove that a dataset is sufficiently anonymized, many privacy policies suggest that a re-identification risk assessment be performed, but do not provide a precise methodology for doing so, leaving the industry alone with the problem.…

The performance of a machine learning system is usually evaluated by using i.i.d.\ observations with true labels. However, acquiring ground truth labels is expensive, while obtaining unlabeled samples may be cheaper. Stratified sampling can…

Classifiers deployed in high-stakes real-world applications must output calibrated confidence scores, i.e. their predicted probabilities should reflect empirical frequencies. Recalibration algorithms can greatly improve a model's…

Latent diffusion models can be used as a powerful augmentation method to artificially extend datasets for enhanced training. To the human eye, these augmented images look very different to the originals. Previous work has suggested to use…

Existing well investigated Predictive Process Monitoring techniques typically construct a predictive model based on past process executions, and then use it to predict the future of new ongoing cases, without the possibility of updating it…

Recent work~\cite{Liu2016} has shown that dependencies between items in a dataset can lead to privacy leaks. We extend this concept to privacy-preserving transformations, considering a broader set of dependencies captured by correlation…

Synthetic data has gained attention for training large language models, but poor-quality data can harm performance (see, e.g., Shumailov et al. (2023); Seddik et al. (2024)). A potential solution is data pruning, which retains only…

This paper adopts Arimoto's $\alpha$-Mutual Information as a tunable privacy measure, in a privacy-preserving data release setting that aims to prevent disclosing private data to adversaries. By fine-tuning the privacy metric, we…

Data-Augmentation (DA) is known to improve performance across tasks and datasets. We propose a method to theoretically analyze the effect of DA and study questions such as: how many augmented samples are needed to correctly estimate the…

Repeated use of a data sample via adaptively chosen queries can rapidly lead to overfitting, wherein the empirical evaluation of queries on the sample significantly deviates from their mean with respect to the underlying data distribution.…

Synthetic data is often presented as a method for sharing sensitive information in a privacy-preserving manner by reproducing the global statistical properties of the original data without disclosing sensitive information about any…

Conformal prediction is a model-agnostic approach to generating prediction sets that cover the true class with a high probability. Although its prediction set size is expected to capture aleatoric uncertainty, there is a lack of evidence…

Numerous generalization techniques have been proposed for privacy preserving data publishing. Most existing techniques, however, implicitly assume that the adversary knows little about the anonymization algorithm adopted by the data…