Fundamental Limits of Membership Inference Attacks on Machine Learning Models
Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the fundamental statistical limitations associated with MIAs on machine learning models at large. More precisely, we first derive the statistical quantity that governs the effectiveness and success of such attacks. We then theoretically prove that in a non-linear regression setting with overfitting learning procedures, attacks may have a high probability of success. Finally, we investigate several situations for which we provide bounds on this quantity of interest. Interestingly, our findings indicate that discretizing the data might enhance the learning procedure's security. Specifically, it is demonstrated to be limited by a constant, which quantifies the diversity of the underlying data distribution. We illustrate those results through simple simulations.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversitySimilar Papers 제목 키워드 기반
OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models
OpenLVLM-MIA is a new benchmark that highlights fundamental challenges in evaluating membership inference attacks (MIA) against large vision-language models (LVLMs). While prior work has reported high attack success rate…
On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models
With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that th…
AttributeBIG-bench Machine LearningInference AttackMachine Learning with Membership Privacy using Adversarial Regularization
Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack,…
BIG-bench Machine LearningGeneral ClassificationInference AttackMembership Inference AttackMembership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
We consider the problem of a training data proof, where a data creator or owner wants to demonstrate to a third party that some machine learning model was trained on their data. Training data proofs play a key role in re…
Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?
Data privacy is an important issue for "machine learning as a service" providers. We focus on the problem of membership inference attacks: given a data sample and black-box access to a model's API, determine whether the …
Machine TranslationTranslationVideo Captioning