Saved in:
Bibliographic Details
Main Authors: Liu, Xuannan, Li, Peipei, Huang, Huaibo, Li, Zekun, Cui, Xing, Liang, Jiahao, Qin, Lixiong, Deng, Weihong, He, Zhaofeng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.01988
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917741791805440
author Liu, Xuannan
Li, Peipei
Huang, Huaibo
Li, Zekun
Cui, Xing
Liang, Jiahao
Qin, Lixiong
Deng, Weihong
He, Zhaofeng
author_facet Liu, Xuannan
Li, Peipei
Huang, Huaibo
Li, Zekun
Cui, Xing
Liang, Jiahao
Qin, Lixiong
Deng, Weihong
He, Zhaofeng
contents The massive generation of multimodal fake news involving both text and images exhibits substantial distribution discrepancies, prompting the need for generalized detectors. However, the insulated nature of training restricts the capability of classical detectors to obtain open-world facts. While Large Vision-Language Models (LVLMs) have encoded rich world knowledge, they are not inherently tailored for combating fake news and struggle to comprehend local forgery details. In this paper, we propose FKA-Owl, a novel framework that leverages forgery-specific knowledge to augment LVLMs, enabling them to reason about manipulations effectively. The augmented forgery-specific knowledge includes semantic correlation between text and images, and artifact trace in image manipulation. To inject these two kinds of knowledge into the LVLM, we design two specialized modules to establish their representations, respectively. The encoded knowledge embeddings are then incorporated into LVLMs. Extensive experiments on the public benchmark demonstrate that FKA-Owl achieves superior cross-domain performance compared to previous methods. Code is publicly available at https://liuxuannan.github.io/FKA_Owl.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01988
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs
Liu, Xuannan
Li, Peipei
Huang, Huaibo
Li, Zekun
Cui, Xing
Liang, Jiahao
Qin, Lixiong
Deng, Weihong
He, Zhaofeng
Computation and Language
The massive generation of multimodal fake news involving both text and images exhibits substantial distribution discrepancies, prompting the need for generalized detectors. However, the insulated nature of training restricts the capability of classical detectors to obtain open-world facts. While Large Vision-Language Models (LVLMs) have encoded rich world knowledge, they are not inherently tailored for combating fake news and struggle to comprehend local forgery details. In this paper, we propose FKA-Owl, a novel framework that leverages forgery-specific knowledge to augment LVLMs, enabling them to reason about manipulations effectively. The augmented forgery-specific knowledge includes semantic correlation between text and images, and artifact trace in image manipulation. To inject these two kinds of knowledge into the LVLM, we design two specialized modules to establish their representations, respectively. The encoded knowledge embeddings are then incorporated into LVLMs. Extensive experiments on the public benchmark demonstrate that FKA-Owl achieves superior cross-domain performance compared to previous methods. Code is publicly available at https://liuxuannan.github.io/FKA_Owl.github.io/.
title FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs
topic Computation and Language
url https://arxiv.org/abs/2403.01988