Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kharlamova, Arina, He, Bowei, Ma, Chen, Liu, Xue
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916990396923904
author Kharlamova, Arina
He, Bowei
Ma, Chen
Liu, Xue
author_facet Kharlamova, Arina
He, Bowei
Ma, Chen
Liu, Xue
contents Online services rely on CAPTCHAs as a first line of defense against automated abuse, yet recent advances in multi-modal large language models (MLLMs) have eroded the effectiveness of conventional designs that focus on text recognition or 2D image understanding. To address this challenge, we present Spatial CAPTCHA, a novel human-verification framework that leverages fundamental differences in spatial reasoning between humans and MLLMs. Unlike existing CAPTCHAs which rely on low-level perception tasks that are vulnerable to modern AI, Spatial CAPTCHA generates dynamic questions requiring geometric reasoning, perspective-taking, occlusion handling, and mental rotation. These skills are intuitive for humans but difficult for state-of-the-art (SOTA) AI systems. The system employs a procedural generation pipeline with constraint-based difficulty control, automated correctness verification, and human-in-the-loop validation to ensure scalability, robustness, and adaptability. Evaluation on a corresponding benchmark, Spatial-CAPTCHA-Bench, demonstrates that humans vastly outperform 10 state-of-the-art MLLMs, with the best model achieving only 31.0% Pass@1 accuracy. Furthermore, we compare Spatial CAPTCHA with Google reCAPTCHA, which confirms its effectiveness as both a security mechanism and a diagnostic tool for spatial reasoning in AI.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03863
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation
Kharlamova, Arina
He, Bowei
Ma, Chen
Liu, Xue
Artificial Intelligence
Cryptography and Security
Online services rely on CAPTCHAs as a first line of defense against automated abuse, yet recent advances in multi-modal large language models (MLLMs) have eroded the effectiveness of conventional designs that focus on text recognition or 2D image understanding. To address this challenge, we present Spatial CAPTCHA, a novel human-verification framework that leverages fundamental differences in spatial reasoning between humans and MLLMs. Unlike existing CAPTCHAs which rely on low-level perception tasks that are vulnerable to modern AI, Spatial CAPTCHA generates dynamic questions requiring geometric reasoning, perspective-taking, occlusion handling, and mental rotation. These skills are intuitive for humans but difficult for state-of-the-art (SOTA) AI systems. The system employs a procedural generation pipeline with constraint-based difficulty control, automated correctness verification, and human-in-the-loop validation to ensure scalability, robustness, and adaptability. Evaluation on a corresponding benchmark, Spatial-CAPTCHA-Bench, demonstrates that humans vastly outperform 10 state-of-the-art MLLMs, with the best model achieving only 31.0% Pass@1 accuracy. Furthermore, we compare Spatial CAPTCHA with Google reCAPTCHA, which confirms its effectiveness as both a security mechanism and a diagnostic tool for spatial reasoning in AI.
title Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation
topic Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2510.03863