paper-with-me

홈 › Papers

AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics

2023-04-14 · Shan Jia, Mingzhen Huang, Zhou Zhou, Yan Ju, Jialing Cai, Siwei Lyu

Recent advancements in language-image models have led to the development of highly realistic images that can be generated from textual descriptions. However, the increased visual quality of these generated images poses a potential threat to the field of media forensics. This paper aims to investigate the level of challenge that language-image generation models pose to media forensics. To achieve this, we propose a new approach that leverages the DALL-E2 language-image model to automatically generate and splice masked regions guided by a text prompt. To ensure the creation of realistic manipulations, we have designed an annotation platform with human checking to verify reasonable text prompts. This approach has resulted in the creation of a new image dataset called AutoSplice, containing 5,894 manipulated and authentic images. Specifically, we have generated a total of 3,621 images by locally or globally manipulating real-world image-caption pairs, which we believe will provide a valuable resource for developing generalized detection methods in this area. The dataset is evaluated under two media forensic tasks: forgery detection and localization. Our extensive experiments show that most media forensic models struggle to detect the AutoSplice dataset as an unseen manipulation. However, when fine-tuned models are used, they exhibit improved performance in both tasks.

📄 PDF Abstract BibTeX arXiv:2304.06870

Code (1)

shanface33/autosplice_dataset 공식 구현

Tasks

Image and Video Forgery DetectionImage Generation

Similar Papers 제목 키워드 기반

VIXEN: Visual Text Comparison Network for Image Difference Captioning

2024-02-29 · Alexander Black, Jing Shi, Yifei Fan, Tu Bui 외

We present VIXEN - a technique that succinctly summarizes in text the visual differences between a pair of images in order to highlight any content manipulation present. Our proposed network linearly maps image features …

Language ModelingLanguage ModellingLarge Language ModelMisinformation

SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization

2026-01-09 · Xinghao Wang, Changtao Miao, Dianmo Sheng, Tao Gong 외 arxiv

Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training expensive. Existing weakly supervised met…

Image Manipulation LocalizationContrastive Learning

Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics

2025-04-16 · Yiran He, Yun Cao, Bowen Yang, Zeyu Zhang

The rapid development of generative AI facilitates content creation and makes image manipulation easier and more difficult to detect. While multimodal Large Language Models (LLMs) have encoded rich world knowledge, they …

Few-Shot LearningImage ManipulationPrompt EngineeringWorld Knowledge

Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

2023-10-24 · Sander Schulhoff, Jeremy Pinto, Anaum Khan, Louis-François Bouchard 외

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively,…

A Large-scale Interpretable Multi-modality Benchmark for Facial Image Forgery Localization

2024-12-27 · Jingchun Lian, Lingyu Liu, Yaxiong Wang, Yujiao Wu 외

Image forgery localization, which centers on identifying tampered pixels within an image, has seen significant advancements. Traditional approaches often model this challenge as a variant of image segmentation, treating …

Face SwappingImage SegmentationLarge Language ModelMultimodal Large Language Model+1