Artificial Intelligence · AI Alignment & Safety
A topic within AI Alignment & Safety, itself one of 11 topics in that field and part of Artificial Intelligence.
2 works
Goodfellow, Shlens & Szegedy
Argues adversarial examples arise from neural networks being too linear rather than too nonlinear, and proposes the fast gradient sign method both as an attack and, used in training, a defence.
11 pageslink checked 17 Sept 2026Szegedy et al.
Shows that imperceptibly small, deliberately chosen perturbations reliably flip a neural network's classification, revealing that the network's learned decision boundaries do not match human perceptual similarity.
10 pageslink checked 17 Sept 2026