相关论文: WaKA: Data Attribution using K-Nearest Neighbors a…

We propose to use precise estimators of mutual information (MI) to find least dependent components in a linearly mixed signal. On the one hand this seems to lead to better blind source separation than with any other presently available…

We study a setting where a data holder wishes to share data with a receiver, without revealing certain summary statistics of the data distribution (e.g., mean, standard deviation). It achieves this by passing the data through a…

Several membership inference (MI) attacks have been proposed to audit a target DNN. Given a set of subjects, MI attacks tell which subjects the target DNN has seen during training. This work focuses on the post-training MI attacks…

The rise of generative image models leads to privacy concerns when it comes to the huge datasets used to train such models. This paper investigates the possibility of inferring if a set of face images was used for fine-tuning a Latent…

The increasing use of diffusion models for image generation, especially in sensitive areas like medical imaging, has raised significant privacy concerns. Membership Inference Attack (MIA) has emerged as a potential approach to determine if…

Deep neural networks are known to be vulnerable to adversarial attacks (AA). For an image recognition task, this means that a small perturbation of the original can result in the image being misclassified. Design of such attacks as well as…

We show that several machine learning estimators, including square-root LASSO (Least Absolute Shrinkage and Selection) and regularized logistic regression can be represented as solutions to distributionally robust optimization (DRO)…

This work aims to address an open problem in data valuation literature concerning the efficient computation of Data Shapley for weighted $K$ nearest neighbor algorithm (WKNN-Shapley). By considering the accuracy of hard-label KNN with…

This paper introduces the Beta distribution as a novel technique to weight direct and indirect trust and assessing the risk in wireless sensor networks. This paper also reviews the trust factors, which play a major role in building trust in…

Membership inference attacks (MIA) aim to infer whether a particular data point is part of the training dataset of a model. In this paper, we propose a new task in the context of LLM privacy: entity-level discovery of membership risk…

Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to…

The advances in machine learning (ML) have greatly improved AI-based diagnosis aid systems in medical imaging. However, being based on collecting medical data specific to individuals induces several security issues, especially in terms of…

The $K$-nearest neighbors is a basic problem in machine learning with numerous applications. In this problem, given a (training) set of $n$ data points with labels and a query point $p$, we want to assign a label to $p$ based on the labels…

A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models. Further, the work of \cite{somesh-overfit} shows that such membership inference…

As large-scale models such as Large Language Models (LLMs) and Large Multimodal Models (LMMs) see increasing deployment, their privacy risks remain underexplored. Membership Inference Attacks (MIAs), which reveal whether a data point was…

Optimization algorithms that seek flatter minima, such as Sharpness-Aware Minimization (SAM), are credited with improved generalization and robustness to noise. We ask whether such gains impact membership privacy. Surprisingly, we find that…

Publishing social network data for research purposes has raised serious concerns for individual privacy. There exist many privacy-preserving works that can deal with different attack models. In this paper, we introduce a novel privacy…

Neural network-based image classifiers are powerful tools for computer vision tasks, but they inadvertently reveal sensitive attribute information about their classes, raising concerns about their privacy. To investigate this privacy…

Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by observing the prediction output of the ML model. While the key…

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…