A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917359490433024 |
|---|---|
| author | Jebreel, Najeeb Sánchez, David Domingo-Ferrer, Josep |
| author_facet | Jebreel, Najeeb Sánchez, David Domingo-Ferrer, Josep |
| contents | Membership inference attacks (MIAs) aim to determine whether a data sample was included in a machine learning (ML) model's training set and have become the de facto standard for measuring privacy leakages in ML. We propose an evaluation framework that defines the conditions under which MIAs constitute a genuine privacy threat, and review representative MIAs against it. We find that, under the realistic conditions defined in our framework, MIAs represent weak privacy threats. Thus, relying on them as a privacy metric in ML can lead to an overestimation of risk and to unnecessary sacrifices in model utility as a consequence of employing too strong defenses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22987 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks Jebreel, Najeeb Sánchez, David Domingo-Ferrer, Josep Cryptography and Security Machine Learning Membership inference attacks (MIAs) aim to determine whether a data sample was included in a machine learning (ML) model's training set and have become the de facto standard for measuring privacy leakages in ML. We propose an evaluation framework that defines the conditions under which MIAs constitute a genuine privacy threat, and review representative MIAs against it. We find that, under the realistic conditions defined in our framework, MIAs represent weak privacy threats. Thus, relying on them as a privacy metric in ML can lead to an overestimation of risk and to unnecessary sacrifices in model utility as a consequence of employing too strong defenses. |
| title | A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2603.22987 |