Related papers: Label-Only Membership Inference Attacks

Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has primarily focused on…

While machine learning (ML) has made tremendous progress during the past decade, recent research has shown that ML models are vulnerable to various security and privacy attacks. So far, most of the attacks in this field focus on…

Membership inference attacks have emerged as a significant privacy concern in the training of deep learning models, where attackers can infer whether a data point was part of the training set based on the model's outputs. To address this…

Recent studies have shown that deep learning models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. To analyze and study these vulnerabilities, various…

Federated Learning is a machine learning setting that reduces direct data exposure, improving the privacy guarantees of machine learning models. Yet, the exchange of model updates between the participants and the aggregator can still leak…

Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy. In particular, fine-tuned models are highly vulnerable, as they are often fine-tuned on small and…

Machine learning models often pose a threat to the privacy of individuals whose data is part of the training set. Several recent attacks have been able to infer sensitive information from trained models, including model inversion or…

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…

Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despite extensive research on MIAs, systematic comparisons between…

Recent studies show that the state-of-the-art deep neural networks are vulnerable to model inversion attacks, in which access to a model is abused to reconstruct private training data of any given target class. Existing attacks rely on…

As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustworthiness has emerged as an imperative challenge for the…

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…

Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning models. We measure…

It is observed in the literature that data augmentation can significantly mitigate membership inference (MI) attack. However, in this work, we challenge this observation by proposing new MI attacks to utilize the information of augmented…

Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…

An efficient scheme is introduced that extends the generalized membership inference attack to every point in a model's training data set. Our approach leverages data partitioning to create variable sized training sets for the reference…

The prosperity of machine learning has also brought people's concerns about data privacy. Among them, inference attacks can implement privacy breaches in various MLaaS scenarios and model training/prediction phases. Specifically, inference…

Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive…

Machine learning (ML) is vulnerable to inference (e.g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of training data or dataset. Existing defenses are only designed…

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…