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 vulnerability of fine-tuned neural networks both empirically and theoretically, the latter using a simplified model of fine-tuning. We show that the vulnerability of non-DP models when measured as the attacker advantage at fixed false positive rate reduces according to a simple power law as the number of examples per class increases, even for the most vulnerable points, but the dataset size needed for adequate protection of the most vulnerable points is very large.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationInference AttackMembership Inference AttackTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
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 observing the prediction output of the ML mod…
FairnessInference AttackL2 RegularizationMembership Inference AttackScrutinizing the Vulnerability of Decentralized Learning to Membership Inference Attacks
The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their premises and without relying on any central…
Effects 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 AttackGLiRA: 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+1Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?
Machine learning has revolutionized numerous domains, playing a crucial role in driving advancements and enabling data-centric processes. The significance of data in training models and shaping their performance cannot b…