arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00045cs.MMcs.AIcs.LG
收藏

检测大型AI模型生成的多媒体:综述

Detecting Multimedia Generated by Large AI Models: A Survey

Department of Computer and Information Technology, Purdue University(普渡大学计算机与信息科技系);School of Software, Nanchang University(南昌大学软件学院);Amazon Prime Video(亚马逊Prime视频);Department of Epidemiology and Biostatistics, School of Public Health(公共卫生学院流行病学与生物统计学系);Department of Computer Science, College of Nanotechnology, Science, and Engineering(纳米技术、科学与工程学院计算机科学系);University at Albany, SUNY(阿尔巴尼大学)

Li Lin, Neeraj Gupta, Yue Zhang, Hainan Ren, Chun-Hao Liu, Feng Ding, Xin Wang, Xin Li, Luisa Verdoliva, Shu Hu

AI总结:

本文首次系统综述LAIM生成文本、图像、视频、音频及多模态内容的检测研究,提出按模态与“纯检测/超越检测”划分的方法分类,并梳理数据集、工具、指标、社会影响及未来方向。

摘要:

大型AI模型(LAIM),尤其是扩散模型和大型语言模型的快速发展,标志着一个新时代的到来,AI生成的多媒体正日益融入日常生活的各个方面。尽管此类内容在众多领域中具有益处,但也带来了重大风险,包括潜在滥用、社会扰乱和伦理问题。因此,检测由LAIM生成的多媒体已变得至关重要,相关研究也显著增加。尽管如此,专门聚焦检测LAIM生成多媒体的系统性综述仍存在明显空白。为弥补这一点,我们提供了首个全面涵盖检测由LAIM创建的多媒体(如文本、图像、视频、音频和多模态内容)现有研究的综述。具体而言,我们提出了一种新颖的检测方法分类体系,按媒体模态进行分类,并与两个视角保持一致:纯检测(旨在提升检测性能)和超越检测(为检测器加入泛化性、鲁棒性和可解释性等属性)。此外,我们简要概述了生成机制、公开数据集、在线检测工具和评估指标,以为该领域的研究人员和从业者提供宝贵资源。最重要的是,我们从社交媒体视角进行了重点分析,以强调其更广泛的社会影响。此外,我们识别了当前检测中的挑战,并提出了未来研究方向,以应对检测LAIM生成多媒体中尚未探索、持续存在和新出现的问题。我们撰写本综述的目标是填补一项学术空白,并为全球AI安全工作作出贡献,帮助确保数字领域的信息完整性。项目链接为 https://github.com/Purdue-M2/Detect-LAIM-generated-Multimedia-Survey。

英文摘要:

The rapid advancement of Large AI Models (LAIMs), particularly diffusion models and large language models, has marked a new era where AI-generated multimedia is increasingly integrated into various aspects of daily life. Although beneficial in numerous fields, this content presents significant risks, including potential misuse, societal disruptions, and ethical concerns. Consequently, detecting multimedia generated by LAIMs has become crucial, with a marked rise in related research. Despite this, there remains a notable gap in systematic surveys that focus specifically on detecting LAIM-generated multimedia. Addressing this, we provide the first survey to comprehensively cover existing research on detecting multimedia (such as text, images, videos, audio, and multimodal content) created by LAIMs. Specifically, we introduce a novel taxonomy for detection methods, categorized by media modality, and aligned with two perspectives: pure detection (aiming to enhance detection performance) and beyond detection (adding attributes like generalizability, robustness, and interpretability to detectors). Additionally, we have presented a brief overview of generation mechanisms, public datasets, online detection tools, and evaluation metrics to provide a valuable resource for researchers and practitioners in this field. Most importantly, we offer a focused analysis from a social media perspective to highlight their broader societal impact. Furthermore, we identify current challenges in detection and propose directions for future research that address unexplored, ongoing, and emerging issues in detecting multimedia generated by LAIMs. Our aim for this survey is to fill an academic gap and contribute to global AI security efforts, helping to ensure the integrity of information in the digital realm. The project link is https://github.com/Purdue-M2/Detect-LAIM-generated-Multimedia-Survey.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑