Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures

Fredrikson, M., Jha, S., & Ristenpart, T. (2015). Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures. Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security (CCS), 1322-1333.

Type

Conference paper

Intellectual base

Primary research

Year

2015

DOI

10.1145/2810103.2813677

Link

https://doi.org/10.1145/2810103.2813677

Cited from

computer_science

Cited by

1 citation across 1 artifact.

Each citation links to the sentence it supports in the citing article.

Primes

• Hidden Information Reconstruction
  • Model, embedding, and gradient inversion: prediction outputs reconstruct training-set faces; vector embeddings reconstruct source text; shared gradients in federated learning reconstruct contributing batches at near-pixel fidelity, defeating the "data never leaves the device" framing.

    This sourceReconstructs recognizable training-set faces from a model's prediction confidences — model inversion.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:7dfe3eefdbb8 · see in the full table