Online reviews in the form of user-generated content (UGC) significantly
impact consumer decision-making. However, the pervasive issue of not only human
fake content but also machine-generated content challenges UGC's reliability.
Recent advances in Large Language Models (LLMs) may pave the way to fabricate
indistinguishable fake generated content at a much lower cost. Leveraging
OpenAI's GPT-4-Turbo and DALL-E-2 models, we craft AiGen-FoodReview, a
multi-modal dataset of 20,144 restaurant review-image pairs divided into
authentic and machine-generated. We explore unimodal and multimodal detection
models, achieving 99.80% multimodal accuracy with FLAVA. We use attributes from
readability and photographic theories to score reviews and images,
respectively, demonstrating their utility as hand-crafted features in scalable
and interpretable detection models, with comparable performance. The paper
contributes by open-sourcing the dataset and releasing fake review detectors,
recommending its use in unimodal and multimodal fake review detection tasks,
and evaluating linguistic and visual features in synthetic versus authentic
data.

通过使用大规模语言模型和图像模型构建 AiGen-FoodReview 数据集，本论文提供了检测和识别机器生成的虚假评论的方法，该方法能在单模态和多模态情况下取得接近真实数据性能的可扩展并可解释的检测结果。

AiGen-FoodReview：一个多模态的机器生成餐厅评论和社交媒体图片的数据集

AiGen-FoodReview: A Multimodal Dataset of Machine-Generated Restaurant  Reviews and Images on Social Media

The fast-spreading information over the internet is essential to support the
rapid supply of numerous public utility services and entertainment to users.
Social networks and online media paved the way for modern,
timely-communication-fashion and convenient access to all types of information.
However, it also provides new chances for ill use of the massive amount of
available data, such as spreading fake content to manipulate public opinion.
Detection of counterfeit content has raised attention in the last few years for
the advances in deepfake generation. The rapid growth of machine learning
techniques, particularly deep learning, can predict fake content in several
application domains, including fake image and video manipulation. This paper
presents a comprehensive review of recent studies for deepfake content
detection using deep learning-based approaches. We aim to broaden the
state-of-the-art research by systematically reviewing the different categories
of fake content detection. Furthermore, we report the advantages and drawbacks
of the examined works and future directions towards the issues and shortcomings
still unsolved on deepfake detection.

本文通过深度学习方法，系统地回顾了近年来深度伪造内容识别的研究，并报告了对于未解决的深伪造检测问题和不足之处的未来方向。

深度学习方法检测深度伪造内容综述

A Review of Deep Learning-based Approaches for Deepfake Content Detection

False information spread via the internet and social media influences public
opinion and user activity, while generative models enable fake content to be
generated faster and more cheaply than had previously been possible. In the not
so distant future, identifying fake content generated by deep learning models
will play a key role in protecting users from misinformation. To this end, a
dataset containing human and computer-generated headlines was created and a
user study indicated that humans were only able to identify the fake headlines
in 47.8% of the cases. However, the most accurate automatic approach,
transformers, achieved an overall accuracy of 85.7%, indicating that content
generated from language models can be filtered out accurately.

通过构建含有人工和计算机生成的标题数据集，研究表明人类只有 47.8% 的准确率识别出虚假标题，而应用于语言模型的 Transformers 却达到了 85.7% 的整体准确率，说明目前的自然语言生成模型可以被识别出来。