// ⛨ Safety, Evaluation & Security
Adversarial Examples (FGSM)
Imperceptible input perturbations that fool models.
对抗样本（FGSM） 2014 Foundational core
IN PLAIN WORDS
A tiny step along the sign of the loss gradient makes models misclassify confidently. The authors blame high-dimensional linearity and propose adversarial training.
Used in: Robustness testing for autonomous driving and face recognition
TIMELINE · prerequisites → this → what builds on it
01Original paper
Explaining and Harnessing Adversarial Examples
Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy · 2014
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Then you can learn
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Courses
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
adversarial-examples)