Pith. sign in

How to backdoor diffusion models? In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4015–4024, 2023

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CR 1

years

2024 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Antelope: Potent and Concealed Jailbreak Attack Strategy

cs.CR · 2024-12-11 · conditional · novelty 4.0

Antelope finds short, inconspicuous suffix tokens by aligning prompt embeddings with reference image embeddings, achieving higher ASR than prior jailbreak attacks on Stable Diffusion and several defenses.

citing papers explorer

Showing 1 of 1 citing paper.

  • Antelope: Potent and Concealed Jailbreak Attack Strategy cs.CR · 2024-12-11 · conditional · none · ref 4

    Antelope finds short, inconspicuous suffix tokens by aligning prompt embeddings with reference image embeddings, achieving higher ASR than prior jailbreak attacks on Stable Diffusion and several defenses.