Explaining and Harnessing Adversarial Examples

Goodfellow, I. J., Shlens, J., & Szegedy, C. (2015). Explaining and Harnessing Adversarial Examples. International Conference on Learning Representations (ICLR).

Type

Preprint

Intellectual base

Grey literature

Year

2015

Link

https://arxiv.org/abs/1412.6572

Cited from

biology_ecology, ethnography_qualitative_methods

Cited by

2 citations across 2 artifacts.

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

Primes

• Negative Case Analysis
  • Policy evaluation: a programme theory that explains observed successes is hardened by deliberately studying the sites or cohorts where it failed. Product research and UX: systematic study of churned users, failed sales, rejected applications, and abandoned carts is negative case analysis on the implicit product theory. Machine learning: adversarial testing, red-teaming, slice analysis, and out-of-distribution evaluation seek inputs that should break the model under its current account of its domain.

    This sourceEstablishes adversarial-example testing — deliberately seeking small worst-case inputs that break a model's implicit account of its domain; the ML instance of disconfirmation search.

• Vaccine Escape
  • In adversarial machine learning it is the input perturbation selected to land just on the wrong side of a learned decision boundary.

    This sourceAdversarial perturbations selected to land just past a learned decision boundary.

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:9ca037d343dd · see in the full table