FGSM (Fast Gradient Sign Method)

anchor

Single-step adversarial attack that perturbs the input along the sign of the loss gradient.

Findings

• IC-028SPADE, an abstaining classifier built on top of ResNet, ViT, and VGG models, detects out-of-distribution and adversarial samples with provable guarantees. [eval]
• IC-077VGG-16's loss landscape barrier height distinguishes adversarial from real inputs, enabling a detection method that outperforms baselines on DeepFool and C&W attacks [eval]