Related papers: Membership Inference Attacks from Causal Principle…
Membership inference (MI) attacks highlight a privacy weakness in present stochastic training methods for neural networks. It is not well understood, however, why they arise. Are they a natural consequence of imperfect generalization only?…
Membership inference attacks (MIAs) have become the standard tool for evaluating privacy leakage in machine learning (ML). Among them, the Likelihood-Ratio Attack (LiRA) is widely regarded as the state of the art when sufficient shadow…
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…
Determining whether a dataset was part of a machine learning model's training data pool can reveal privacy vulnerabilities, a challenge often addressed through membership inference attacks (MIAs). Traditional MIAs typically require access…
Deep learning models often raise privacy concerns as they leak information about their training data. This enables an adversary to determine whether a data point was in a model's training set by conducting a membership inference attack…
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…
The lack of data transparency in Large Language Models (LLMs) has highlighted the importance of Membership Inference Attack (MIA), which differentiates trained (member) and untrained (non-member) data. Though it shows success in previous…
Membership inference attacks aim to detect if a particular data point was used in training a model. We design a novel statistical test to perform robust membership inference attacks (RMIA) with low computational overhead. We achieve this by…
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…
The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a…
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…
Membership inference attacks (MIAs) have been extensively studied in large language models (LLMs) and vision-language models (VLMs), yet their implications for vision-language-action (VLA) models remain largely unexplored. VLA models differ…
The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs). Despite numerous MIA studies,…
Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…
The membership inference attack (MIA) is a popular paradigm for compromising the privacy of a machine learning (ML) model. MIA exploits the natural inclination of ML models to overfit upon the training data. MIAs are trained to distinguish…
A Membership Inference Attack (MIA) assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or…
Fine-tuned language models pose significant privacy risks, as they may memorize and expose sensitive information from their training data. Membership inference attacks (MIAs) provide a principled framework for auditing these risks, yet…
Membership Inference Attack (MIA) aims to determine whether a specific data sample was included in the training dataset of a target model. Traditional MIA approaches rely on shadow models to mimic target model behavior, but their…
Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these attacks are applied to pre-trained large language models (LLMs), they encounter significant…
Membership inference attacks (MIAs) on diffusion models have emerged as potential evidence of unauthorized data usage in training pre-trained diffusion models. These attacks aim to detect the presence of specific images in training datasets…