SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark
J Niu, X Zhu, M Zeng, G Zhang, Q Zhao… - arXiv preprint arXiv …, 2023 - arxiv.org
Membership inference (MI) attacks threaten user privacy through determining if a given data
example has been used to train a target model. However, it has been increasingly …
example has been used to train a target model. However, it has been increasingly …
Enhanced mixup training: a defense method against membership inference attack
Membership inference attacks (MIAs) have powerful attack ability to threaten the privacy of
users. In general, it mainly utilizes model-based or metric-based inference methods to infer …
users. In general, it mainly utilizes model-based or metric-based inference methods to infer …
[HTML][HTML] A survey on membership inference attacks and defenses in Machine Learning
Membership inference (MI) attacks mainly aim to infer whether a data record was used to
train a target model or not. Due to the serious privacy risks, MI attacks have been attracting a …
train a target model or not. Due to the serious privacy risks, MI attacks have been attracting a …
Sok: Membership inference is harder than previously thought
A Dionysiou, E Athanasopoulos - Proceedings on Privacy …, 2023 - petsymposium.org
Membership Inference Attacks (MIAs) can be conducted based on specific
settings/assumptions and experience different limitations. In this paper, first, we provide a …
settings/assumptions and experience different limitations. In this paper, first, we provide a …
Practical blind membership inference attack via differential comparisons
Membership inference (MI) attacks affect user privacy by inferring whether given data
samples have been used to train a target learning model, eg, a deep neural network. There …
samples have been used to train a target learning model, eg, a deep neural network. There …
Dissecting membership inference risk in machine learning
N Senavirathne, V Torra - … 13th International Symposium, CSS 2021, Virtual …, 2022 - Springer
Membership inference attacks (MIA) have been identified as a distinct threat to privacy when
sensitive personal data are used to train the machine learning (ML) models. This work is …
sensitive personal data are used to train the machine learning (ML) models. This work is …
[HTML][HTML] Dual Defense: Combining Preemptive Exclusion of Members and Knowledge Distillation to Mitigate Membership Inference Attacks
Membership inference (MI) attacks threaten user privacy through determining if a given data
example has been used to train a target model. Existing MI defenses protect the …
example has been used to train a target model. Existing MI defenses protect the …
[HTML][HTML] Scalable membership inference attacks via quantile regression
Membership inference attacks are designed to determine, using black box access to trained
models, whether a particular example was used in training or not. Membership inference …
models, whether a particular example was used in training or not. Membership inference …
Why train more? effective and efficient membership inference via memorization
Membership Inference Attacks (MIAs) aim to identify specific data samples within the private
training dataset of machine learning models, leading to serious privacy violations and other …
training dataset of machine learning models, leading to serious privacy violations and other …
Data and model dependencies of membership inference attack
Machine learning (ML) models have been shown to be vulnerable to Membership Inference
Attacks (MIA), which infer the membership of a given data point in the target dataset by …
Attacks (MIA), which infer the membership of a given data point in the target dataset by …