Sign inSign in
ConceptAI & ML

Membership inference attack

Determining whether a specific data point was part of a model's training set by measuring the model's loss on that point.
as Ashwinee Panda defines itCaltechThe wording closest to all 4 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Machine learning models3Language model2Training data2Black-box model access1False positive and false negative rates1Loss score1Privacy auditing1Privacy in machine learning1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

4

Each in their own terms, from the easiest level.

  • Robin Staab

    Caltech · Graduate

    A privacy evaluation approach examining whether specific data samples were part of a model's training set.
    • 2:55Emerging Threats in LLM Privacy and Poisoning
  • Moritz Knolle

    Caltech · Graduate

    Attacks on machine learning models where an adversary determines whether a specific data record was part of the training dataset.
    • 3:30Disparate Privacy Risks from Medical AI: Patient-level Auditing
  • Ryoto Koike

    Google Research & TechTalks · Research

    A task to determine whether a specific text was included in the training data of a target language model.
    • 31:10Machine Text Detectors are Membership Inference Attacks

Lectures that assume it

1

Connections

12

The lectures that define it or assume it, and the concepts next to it.

4 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.