pith. sign in

For a clean sample x with label y, and a target neural network fθ, the adversary aims to produce xadv by introducing adversarial perturbations

PROPOSED METHOD We propose a novel defense strategy against adversarial attacks on classification models by leveraging language guidance in diffusion models for adversarial pur

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.LG 1

years

2023 1

verdicts

UNVERDICTED 1

representative citing papers

Language Guided Adversarial Purification

cs.LG · 2023-09-19 · unverdicted · novelty 6.0

LGAP generates captions from images to guide diffusion-based purification, outperforming other adversarial defenses without specialized training.

citing papers explorer

Showing 1 of 1 citing paper.

  • Language Guided Adversarial Purification cs.LG · 2023-09-19 · unverdicted · none · ref 5

    LGAP generates captions from images to guide diffusion-based purification, outperforming other adversarial defenses without specialized training.