Related papers: Model Inversion Robustness: Can Transfer Learning …

Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy. To mitigate this vulnerability, prior work proposed both principled defenses…

A Model Inversion (MI) attack based on Generative Adversarial Networks (GAN) aims to recover the private training data from complex deep learning models by searching codes in the latent space. However, they merely search a deterministic…

Model Inversion (MI) attacks, which reconstruct the training dataset of neural networks, pose significant privacy concerns in machine learning. Recent MI attacks have managed to reconstruct realistic label-level private data, such as the…

Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate privacy risks by mapping facial images to embeddings (commonly regarded as privacy-preserving), model…

Model inversion (MI) attacks aim to infer or reconstruct the training dataset through reverse-engineering from the target model's weights. Recently, significant advancements in generative models have enabled MI attacks to overcome…

Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training data. To defend against MI attacks, previous work utilizes a…

Model inversion attacks pose a significant privacy threat to machine learning models by reconstructing sensitive data from their outputs. While various defenses have been proposed to counteract these attacks, they often come at the cost of…

These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…

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…

Model-sharing offers significant business value by enabling firms with well-established Machine Learning (ML) models to monetize and share their models with others who lack the resources to develop ML models from scratch. However, concerns…

With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an adversary to obtain private information about the types of…

Model inversion attacks involve reconstructing the training data of a target model, which raises serious privacy concerns for machine learning models. However, these attacks, especially learning-based methods, are likely to suffer from low…

Many data mining tasks rely on graphs to model relational structures among individuals (nodes). Since relational data are often sensitive, there is an urgent need to evaluate the privacy risks in graph data. One famous privacy attack…

As machine learning becomes more widely used for critical applications, the need to study its implications in privacy turns to be urgent. Given access to the target model and auxiliary information, the model inversion attack aims to infer…

Model inversion (MI) attacks allow to reconstruct average per-class representations of a machine learning (ML) model's training data. It has been shown that in scenarios where each class corresponds to a different individual, such as face…

Increasing use of machine learning (ML) technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing…

Transfer learning is an important approach that produces pre-trained teacher models which can be used to quickly build specialized student models. However, recent research on transfer learning has found that it is vulnerable to various…

Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that…

We describe a threat model under which a split network-based federated learning system is susceptible to a model inversion attack by a malicious computational server. We demonstrate that the attack can be successfully performed with limited…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…