Watertox combines a two-stage FGSM with a four-model ensemble vote to generate adversarial images that reportedly reduce unseen-model accuracy by up to 98.8%.
Enhancing the transferability of adversarial attacks through variance tuning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
Watertox: The Art of Simplicity in Universal Attacks A Cross-Model Framework for Robust Adversarial Generation
Watertox combines a two-stage FGSM with a four-model ensemble vote to generate adversarial images that reportedly reduce unseen-model accuracy by up to 98.8%.