Turning Adversaries into Allies: Reversing Typographic Attacks for Multimodal E-Commerce Product Retrieval

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jenq, Janet, Shen, Hongda
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914142596628480
author Jenq, Janet
Shen, Hongda
author_facet Jenq, Janet
Shen, Hongda
contents Multimodal product retrieval systems in e-commerce platforms rely on effectively combining visual and textual signals to improve search relevance and user experience. However, vision-language models such as CLIP are vulnerable to typographic attacks, where misleading or irrelevant text embedded in images skews model predictions. In this work, we propose a novel method that reverses the logic of typographic attacks by rendering relevant textual content (e.g., titles, descriptions) directly onto product images to perform vision-text compression, thereby strengthening image-text alignment and boosting multimodal product retrieval performance. We evaluate our method on three vertical-specific e-commerce datasets (sneakers, handbags, and trading cards) using six state-of-the-art vision foundation models. Our experiments demonstrate consistent improvements in unimodal and multimodal retrieval accuracy across categories and model families. Our findings suggest that visually rendering product metadata is a simple yet effective enhancement for zero-shot multimodal retrieval in e-commerce applications.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05325
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Turning Adversaries into Allies: Reversing Typographic Attacks for Multimodal E-Commerce Product Retrieval
Jenq, Janet
Shen, Hongda
Machine Learning
Multimodal product retrieval systems in e-commerce platforms rely on effectively combining visual and textual signals to improve search relevance and user experience. However, vision-language models such as CLIP are vulnerable to typographic attacks, where misleading or irrelevant text embedded in images skews model predictions. In this work, we propose a novel method that reverses the logic of typographic attacks by rendering relevant textual content (e.g., titles, descriptions) directly onto product images to perform vision-text compression, thereby strengthening image-text alignment and boosting multimodal product retrieval performance. We evaluate our method on three vertical-specific e-commerce datasets (sneakers, handbags, and trading cards) using six state-of-the-art vision foundation models. Our experiments demonstrate consistent improvements in unimodal and multimodal retrieval accuracy across categories and model families. Our findings suggest that visually rendering product metadata is a simple yet effective enhancement for zero-shot multimodal retrieval in e-commerce applications.
title Turning Adversaries into Allies: Reversing Typographic Attacks for Multimodal E-Commerce Product Retrieval
topic Machine Learning
url https://arxiv.org/abs/2511.05325