Related papers: Bayesian Inference of Training Dataset Membership
Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set. While existing methods typically rely on measuring reconstruction error across…
Whether LLMs memorize their training data and what this means, from measuring privacy leakage to detecting copyright violations, has become a rapidly growing area of research. In the last few months, more than 10 new methods have been…
Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary data holders who are not ML experts can apply off-the-shelf…
Membership inference attacks (MIAs) on code completion models offer an effective way to assess privacy risks by inferring whether a given code snippet was part of the training data. Existing black- and gray-box MIAs rely on expensive…
Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the training set data. Membership Inference Attacks (MIAs) exploit…
Large Language Models (LLMs) and Vision-Language Models (VLMs) have made significant advancements in a wide range of natural language processing and vision-language tasks. Access to large web-scale datasets has been a key factor in their…
Model explanations improve the transparency of black-box machine learning (ML) models and their decisions; however, they can also be exploited to carry out privacy threats such as membership inference attacks (MIA). Existing works have only…
Membership inference (MI) attack is currently the most popular test for measuring privacy leakage in machine learning models. Given a machine learning model, a data point and some auxiliary information, the goal of an MI attack is to…
Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency to memorize training data raises serious privacy and…
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…
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they…
In recent years, the widespread adoption of Machine Learning as a Service (MLaaS), particularly in sensitive environments, has raised considerable privacy concerns. Of particular importance are membership inference attacks (MIAs), which…
Neural models for vulnerability prediction (VP) have achieved impressive performance by learning from large-scale code repositories. However, their susceptibility to Membership Inference Attacks (MIAs), where adversaries aim to infer…
Membership inference (MI) determines if a sample was part of a victim model training set. Recent development of MI attacks focus on record-level membership inference which limits their application in many real-world scenarios. For example,…
Membership inference attacks (MIAs) are widely used to empirically assess privacy risks in machine learning models, both providing model-level vulnerability metrics and identifying the most vulnerable training samples. State-of-the-art…
While in-processing fairness approaches show promise in mitigating biased predictions, their potential impact on privacy leakage remains under-explored. We aim to address this gap by assessing the privacy risks of fairness-enhanced binary…
Quantizing machine learning models has demonstrated its effectiveness in lowering memory and inference costs while maintaining performance levels comparable to those of the original models. In this work, we investigate the impact of…
Membership Inference Attacks (MIAs) pose a significant privacy risk by enabling adversaries to determine if a specific data point was part of a model's training set. This work empirically investigates whether MU algorithms can function as a…
Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we investigate the vulnerability of diffusion models to…
Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset. Existing attack methods have commonly…