Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures

Matt Fredrikson; Somesh Jha; Thomas Ristenpart

doi:https://doi.org/10.1145/2810103.2813677

Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures

2015 · 2,885 citations · 12 from inside this corpus

Matt Fredrikson, Somesh Jha, Thomas Ristenpart

The source holds an abstract for this work, but its best open-access copy is under no open licence, which does not permit us to republish the text. Read it at the source below.

14 of 14 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

Deep Learning with Differential Privacy→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Advances and Open Problems in Federated Learning→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Membership Inference Attacks Against Machine Learning Models→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Practical Secure Aggregation for Privacy-Preserving Machine Learning→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Federated Learning in Mobile Edge Networks: A Comprehensive Survey→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Federated Learning With Differential Privacy: Algorithms and Performance Analysis→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
On the Opportunities and Risks of Foundation Models→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference A…→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Accessorize to a Crime→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Deep Leakage from Gradients→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Secure, privacy-preserving and federated machine learning in medical imaging→Model Inversion Attacks that Exploit Confidence Information and Basic CountermeasuresLegacy edge — source detail unavailable
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures→Differential PrivacyLegacy edge — source detail unavailable
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures→Robust De-anonymization of Large Sparse DatasetsLegacy edge — source detail unavailable
Robust De-anonymization of Large Sparse Datasets→Differential PrivacyLegacy edge — source detail unavailable
Membership Inference Attacks Against Machine Learning Models→Deep Learning with Differential PrivacyLegacy edge — source detail unavailable
Practical Secure Aggregation for Privacy-Preserving Machine Learning→Robust De-anonymization of Large Sparse DatasetsLegacy edge — source detail unavailable
Practical Secure Aggregation for Privacy-Preserving Machine Learning→Deep Learning with Differential PrivacyLegacy edge — source detail unavailable
Practical Secure Aggregation for Privacy-Preserving Machine Learning→Membership Inference Attacks Against Machine Learning ModelsLegacy edge — source detail unavailable
Practical Secure Aggregation for Privacy-Preserving Machine Learning→Differential PrivacyLegacy edge — source detail unavailable
Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference A…→Deep Learning with Differential PrivacyLegacy edge — source detail unavailable
Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference A…→Membership Inference Attacks Against Machine Learning ModelsLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Deep Learning with Differential PrivacyLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Membership Inference Attacks Against Machine Learning ModelsLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Accessorize to a CrimeLegacy edge — source detail unavailable
Deep Leakage from Gradients→Membership Inference Attacks Against Machine Learning ModelsLegacy edge — source detail unavailable
Advances and Open Problems in Federated Learning→Deep Learning with Differential PrivacyLegacy edge — source detail unavailable
Advances and Open Problems in Federated Learning→Membership Inference Attacks Against Machine Learning ModelsLegacy edge — source detail unavailable
Advances and Open Problems in Federated Learning→Practical Secure Aggregation for Privacy-Preserving Machine LearningLegacy edge — source detail unavailable
Federated Learning in Mobile Edge Networks: A Comprehensive Survey→Deep Learning with Differential PrivacyLegacy edge — source detail unavailable
Federated Learning in Mobile Edge Networks: A Comprehensive Survey→Membership Inference Attacks Against Machine Learning ModelsLegacy edge — source detail unavailable
Federated Learning in Mobile Edge Networks: A Comprehensive Survey→Practical Secure Aggregation for Privacy-Preserving Machine LearningLegacy edge — source detail unavailable
Federated Learning With Differential Privacy: Algorithms and Performance Analysis→Deep Learning with Differential PrivacyLegacy edge — source detail unavailable
Secure, privacy-preserving and federated machine learning in medical imaging→Robust De-anonymization of Large Sparse DatasetsLegacy edge — source detail unavailable
Secure, privacy-preserving and federated machine learning in medical imaging→Membership Inference Attacks Against Machine Learning ModelsLegacy edge — source detail unavailable
On the Opportunities and Risks of Foundation Models→Membership Inference Attacks Against Machine Learning ModelsLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
Differential Privacy	2006	5,337
Robust De-anonymization of Large Sparse Datasets	2008	2,349

What cites it, inside the corpus

Paper	Year	Cited
Deep Learning with Differential Privacy	2016	6,220
Advances and Open Problems in Federated Learning	2020	5,383
Membership Inference Attacks Against Machine Learning Models	2017	4,490
Practical Secure Aggregation for Privacy-Preserving Machine Learning	2017	3,744
Federated Learning in Mobile Edge Networks: A Comprehensive Survey	2020	2,538
Federated Learning With Differential Privacy: Algorithms and Performance Analysis	2020	2,357
On the Opportunities and Risks of Foundation Models	2021	2,265
Adversarial Examples: Attacks and Defenses for Deep Learning	2019	1,786
Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference A…	2019	1,624
Accessorize to a Crime	2016	1,596
Deep Leakage from Gradients	2020	1,532
Secure, privacy-preserving and federated machine learning in medical imaging	2020	1,454

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Privacy-Preserving Technologies in Data	Computer Science
Adversarial Robustness in Machine Learning	Computer Science
Autopsy Techniques and Outcomes	Medicine

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

supports3 author record(s) attached.
supports29 reference(s) recorded.
neutralThe DOI carries no year to check against.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:48+00:00.

sha256 46f669157f96ea35…