A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks.

Lee, K., Lee, K., Lee, H., & Shin, J. (2018). A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. Advances in Neural Information Processing Systems.

Type

Book chapter

Intellectual base

Review or monograph

Year

2018

Link

https://proceedings.neurips.cc/paper/2018/hash/abdeb6f575ac5c6676b747bca8d09cc2-Abstract.html

Cited from

computer_science

Cited by

1 citation across 1 artifact.

Primes

• Out Of Distribution Detection
  • A standard construction uses the Mahalanobis distance of the input's feature representation to the nearest class-conditional Gaussian fitted on training features: in-distribution inputs land close to a training cluster (low distance), genuinely novel inputs land far (high distance).

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:9d235d5ca5be · see in the full table