Signals 4 · free daily AI digest

Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers

Paper recorded by Signals 4 on 2026-09-25 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.CL · 自然语言处理 · first seen 2026-09-28

Abstract

Vision-language models (VLMs), despite their success in optical character recognition (OCR) tasks, are vulnerable to typographic attacks and have a fragile structure for images with multiple text layers. In this study, the DecoyBench dataset was created using the Decoy Font method. The dataset consists of 300 images, each containing text with sharp contour lines superimposed on another text with s

Read on arXiv →

#8 most recent of 267 cs.CL papers we have recorded · ↑ newer: Towards Mitigating Fabricated Consensus: The Active Provenance Gate fo · ↓ older: Intent2Tc: Automated Intent-to-Traffic Control Translation with Langua
Cite this page: Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers: the #8 most recent of 267 cs.CL papers we have recorded (as of 2026-09-25). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/sorry-robot-happy-human-vision-language-models-read-only-one-of-two-legible-typo.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions