Related papers: Ensemble Privacy Defense for Knowledge-Intensive L…

As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used during training, despite growing concerns about their…

State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a result, prior research has either relied on…

Deep learning models, while achieving remarkable performances, are vulnerable to membership inference attacks (MIAs). Although various defenses have been proposed, there is still substantial room for improvement in the privacy-utility…

OpenLVLM-MIA is a new benchmark that highlights fundamental challenges in evaluating membership inference attacks (MIA) against large vision-language models (LVLMs). While prior work has reported high attack success rates, our analysis…

Image-to-image translation models are shown to be vulnerable to the Membership Inference Attack (MIA), in which the adversary's goal is to identify whether a sample is used to train the model or not. With daily increasing applications based…

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…

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…

Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of…

Recently, adapting the idea of self-supervised learning (SSL) on continuous speech has started gaining attention. SSL models pre-trained on a huge amount of unlabeled audio can generate general-purpose representations that benefit a wide…

Foundation-style ECG encoders pretrained with self-supervised learning are increasingly reused across tasks, institutions, and deployment contexts, often through model-as-a-service interfaces that expose scalar scores or latent…

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…

Recently, large language models (LLMs) have been gaining a lot of interest due to their adaptability and extensibility in emerging applications, including communication networks. It is anticipated that ZSM networks will be able to support…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…

Membership inference attacks (MIAs) aim to determine whether a specific example was used to train a given language model. While prior work has explored prompt-based attacks such as ReCALL, these methods rely heavily on the assumption that…

Spiking Neural Networks (SNNs) are increasingly explored for their energy efficiency and robustness in real-world applications, yet their privacy risks remain largely unexamined. In this work, we investigate the susceptibility of SNNs to…

Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly influential in shaping user behavior and decision-making, highlighting their…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…

With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. However, their…

With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in…