相关论文: Noisy Neighbors: Efficient membership inference at…

Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…

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…

Transfer learning has been widely studied and gained increasing popularity to improve the accuracy of machine learning models by transferring some knowledge acquired in different training. However, no prior work has pointed out that…

We study the privacy implications of training recurrent neural networks (RNNs) with sensitive training datasets. Considering membership inference attacks (MIAs), which aim to infer whether or not specific data records have been used in…

Membership inference attacks (MIAs) are currently considered one of the main privacy attack strategies, and their defense mechanisms have also been extensively explored. However, there is still a gap between the existing defense approaches…

While Membership Inference Attacks (MIAs) are the prevailing method for identifying training data, their application has expanded into privacy auditing and machine unlearning. Nevertheless, the field lacks a systematic framework for…

In Embedding-as-an-Interface (EaaI) settings, pre-trained models are queried for Intermediate Representations (IRs). The distributional properties of IRs can leak training-set membership signals, enabling Membership Inference Attacks (MIAs)…

Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training…

In this paper we develop state-of-the-art privacy attacks against Large Language Models (LLMs), where an adversary with some access to the model tries to learn something about the underlying training data. Our headline results are new…

Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data. Empowered by large-scale parameters, these models often exhibit strong memorization of their training data,…

Membership Inference Attacks (MIAs) expose privacy risks by determining whether a specific sample was part of a model's training set. These threats are especially serious in sensitive domains such as healthcare and finance. Traditional…

Federated Large Language Models (FedLLMs) enable multiple parties to collaboratively fine-tune LLMs without sharing raw data, addressing challenges of limited resources and privacy concerns. Despite data localization, shared gradients can…

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership…

The rapid advancement of diffusion-based image generation models has raised serious concerns regarding potential copyright and privacy infringements involving human-created data. Membership inference attacks (MIAs) have emerged as a…

The proliferation of large language models (LLMs) in the real world has come with a rise in copyright cases against companies for training their models on unlicensed data from the internet. Recent works have presented methods to identify if…

Membership Inference Attacks (MIA) enable to empirically assess the privacy of a machine learning algorithm. In this paper, we propose TAMIS, a novel MIA against differentially-private synthetic data generation methods that rely on…

While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). This paper presents an empirical evaluation of Differential Privacy (DP) as a defense…

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…

Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MIA vulnerability is often evaluated through…

Large Reasoning Models (LRMs) have rapidly gained prominence for their strong performance in solving complex tasks. Many modern black-box LRMs expose the intermediate reasoning traces through APIs to improve transparency (e.g., Gemini-2.5…