Live briefing
Everything about Model inversion attack
Type of adversarial machine learning attack
Model inversion attack is a type of adversarial machine learning attack where an attacker tries to reconstruct or infer sensitive information about a model's training data by analyzing the outputs of a trained machine learning model. Instead of directly querying the underlying dataset, attackers query the model, and leverage patterns in the model responses to infer properties of the original inputs. These attacks leverage the fact that machine learning models encode statistical information about their training data in their parameters and outputs, which can unintentionally leak private or proprietary information. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Model inversion attackA 5-minute orientation
- Skim a recent paper: Vulnerability of State-of-the-Art Face Recognition Models to Template Inversion AttackInfluential work since 2022
- Pick up a classic book: Treaty Occupationay ToxicologyThe most-reprinted book on the subject
- Read the landmark paper: Model Inversion Attack by Integration of Deep Generative Models: Privacy-Sensitive Face Generation From a Face Recognition SystemCited 91 times
- Go sideways: Membership inference attackA closely related topic
- Go sideways: Adversarial machine learningA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
No outline available.
🏆 Landmark papers (most cited)
Model Inversion Attack by Integration of Deep Generative Models: Privacy-Sensitive Face Generation From a Face Recognition System
Label-Only Model Inversion Attacks: Attack With the Least Information
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
Unstoppable Attack: Label-Only Model Inversion Via Conditional Diffusion Model
An Attack-Based Evaluation Method for Differentially Private Learning Against Model Inversion Attack
C2FMI: Corse-to-Fine Black-Box Model Inversion Attack
Querying little is enough: Model inversion attack via latent information
Model Inversion Attack: Analysis under Gray-box Scenario on Deep Learning based Face Recognition System
🆕 Influential since 2022
Vulnerability of State-of-the-Art Face Recognition Models to Template Inversion Attack
IPRemover: A Generative Model Inversion Attack against Deep Neural Network Fingerprinting and Watermarking
An empirical analysis of image augmentation against model inversion attack in federated learning
Model Inversion Attack Against Federated Unlearning
Model Inversion Attack Against Transfer Learning: Inverting a Model Without Querying It
📚 Books worth reading
Treaty Occupationay ToxicologySuelen Queiroz · 2010
TCP/IP IllustratedW. Richard Stevens, Kevin R. Fall · 1993
Coding the MatrixPhilip N. Klein · 2013- 📕Technologies for optical countermeasures VID. H. Titterton, Richardson, Mark A. Dr · 2009
- 📕Applied Aerodynamics Conference 2014Great Britain) Applied Aerodynamics Conference (2014 Bristol · 2014
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Membership inference attack A membership inference attack (MIA) is a privacy attack that infers whether a record was included in the set of data used to produce a given output, such…
- Adversarial machine learning Adversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks. Machine learning techniques…
- Nicholas Carlini Nicholas Carlini is an American researcher affiliated with Anthropic and previously with Google DeepMind who has published research in the fields of computer…
- Self-supervised learning Self-supervised learning (SSL) is a paradigm in machine learning where a model is trained on a task using the data itself to generate supervisory signals…
- Conformal prediction Conformal prediction (CP) is an algorithm for uncertainty quantification that produces statistically valid prediction regions (multidimensional prediction…
- Differentially private stochastic gradient descent Differentially private stochastic gradient descent (DP-SGD) is an algorithmic technique for learning and a refined analysis of privacy costs within the…
- Deep learning In machine learning, deep learning (DL) focuses on utilizing multilayered neural networks to perform tasks such as classification, regression, and representatio…
- Concept drift In predictive analytics, data science, machine learning and related fields, concept drift or drift is an evolution of data that invalidates the data model…