Transferability
-
How Adversarial Examples Fool Image Classifiers
Adversarial examples follow the model's own gradient: a 0.007 per-pixel nudge made GoogLeNet call a panda a gibbon at 99.3%. How and why it works.
-
CLIP Adversarial Attacks: One Perturbation, Every Model
CLIP is the shared vision encoder under most multimodal systems, which is why one universal perturbation now transfers across encoders, tasks and domains.
-
Adversarial Transferability: How Black-Box Attacks Work
Adversarial examples transfer across models with different architectures and training sets. Why that happens, and what it means for black-box defenses.