Pith. sign in

The claude 3 model family: Opus, sonnet, haiku

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

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Transferable Adversarial Attacks on Black-Box Vision-Language Models

cs.CV · 2025-05-02 · conditional · novelty 6.0

Targeted, barely visible image perturbations transfer from open-source surrogate models to proprietary black-box VLLMs like GPT-4o, Claude, and Gemini, achieving high attack success on captioning, VQA, and receipt text recognition.

citing papers explorer

Showing 1 of 1 citing paper.

  • Transferable Adversarial Attacks on Black-Box Vision-Language Models cs.CV · 2025-05-02 · conditional · none · ref 6

    Targeted, barely visible image perturbations transfer from open-source surrogate models to proprietary black-box VLLMs like GPT-4o, Claude, and Gemini, achieving high attack success on captioning, VQA, and receipt text recognition.