On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Models
Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model. It is a threat while being in the training data is private information of a data point. MIA correctly infers some data points as members or non-members of the training data. Intuitively, data points that MIA accurately detects are vulnerable. Considering those data points may exist in different target models susceptible to multiple MIAs, the vulnerability of data points under multiple MIAs and target models is worth exploring. This paper defines new metrics that can reflect the actual situation of data points' vulnerability and capture vulnerable data points under multiple MIAs and target models. From the analysis, MIA has an inference tendency to some data points despite a low overall inference performance. Additionally, we implement 54 MIAs, whose average attack accuracy ranges from 0.5 to 0.9, to support our analysis with our scalable and flexible platform, Membership Inference Attacks Platform (VMIAP). Furthermore, previous methods are unsuitable for finding vulnerable data points under multiple MIAs and different target models. Finally, we observe that the vulnerability is not characteristic of the data point but related to the MIA and target model.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
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 v…
Image ClassificationInference AttackMembership Inference AttackTransfer LearningAssessing Per-Sample Membership Inference Vulnerability without Retraining
Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the followin…
The Tail Tells All: Estimating Model-Level Membership Inference Vulnerability Without Reference Models
Membership inference attacks (MIAs) have emerged as the standard tool for evaluating the privacy risks of AI models. However, state-of-the-art attacks require training numerous, often computationally expensive, reference…
GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
While Deep Neural Networks (DNNs) have demonstrated remarkable performance in tasks related to perception and control, there are still several unresolved concerns regarding the privacy of their training data, particularl…
image-classificationImage ClassificationInference AttackKnowledge Distillation+1Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three …
Inference AttackMembership Inference Attack