Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models

TL;DR

This paper introduces DeceptionDecoded, a large-scale benchmark dataset for detecting misleading creator intent in multimodal news, revealing current vision-language models' struggles and proposing data synthesis to improve intent reasoning.

Contribution

The paper presents DeceptionDecoded, a novel dataset and framework for modeling and detecting misleading intent in multimodal misinformation, enhancing model robustness.

Findings

14 state-of-the-art VLMs struggle with intent reasoning

Models rely on shallow cues like surface alignment and stylistic signals

Training on DeceptionDecoded improves transferability to real-world MMD

Abstract

The impact of multimodal misinformation arises not only from factual inaccuracies but also from the misleading narratives that creators deliberately embed. Interpreting such creator intent is therefore essential for multimodal misinformation detection (MMD) and effective information governance. To this end, we introduce DeceptionDecoded, a large-scale benchmark of 12,000 image-caption pairs grounded in trustworthy reference articles, created using an intent-guided simulation framework that models both the desired influence and the execution plan of news creators. The dataset captures both misleading and non-misleading cases, spanning manipulations across visual and textual modalities, and supports three intent-centric tasks: (1) misleading intent detection, (2) misleading source attribution, and (3) creator desire inference. We evaluate 14 state-of-the-art vision-language models (VLMs) and find that they struggle with intent reasoning, often relying on shallow cues such as surface-level alignment, stylistic polish, or heuristic authenticity signals. To bridge this, our framework systematically synthesizes data that enables models to learn implication-level intent reasoning. Models trained on DeceptionDecoded demonstrate strong transferability to real-world MMD, validating our framework as both a benchmark to diagnose VLM fragility and a data synthesis engine that provides high-quality, intent-focused resources for enhancing robustness in real-world multimodal misinformation governance.