DREAM: A Benchmark Study for Deepfake REalism AssessMent

• URL: http://arxiv.org/abs/2510.10053v1
• Date: Sat, 11 Oct 2025 06:41:49 GMT
• Title: DREAM: A Benchmark Study for Deepfake REalism AssessMent
• Authors: Bo Peng, Zichuan Wang, Sheng Yu, Xiaochuan Jin, Wei Wang, Jing Dong,
• Abstract summary: This paper presents a comprehensive benchmark called DREAM, which stands for Deepfake REalism AssessMent.<n>It is comprised of a deepfake video dataset of diverse quality, a large scale annotation that includes 140,000 realism scores and textual descriptions obtained from 3,500 human annotators.
• Score: 12.366894730959809
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning based face-swap videos, widely known as deepfakes, have drawn wide attention due to their threat to information credibility. Recent works mainly focus on the problem of deepfake detection that aims to reliably tell deepfakes apart from real ones, in an objective way. On the other hand, the subjective perception of deepfakes, especially its computational modeling and imitation, is also a significant problem but lacks adequate study. In this paper, we focus on the visual realism assessment of deepfakes, which is defined as the automatic assessment of deepfake visual realism that approximates human perception of deepfakes. It is important for evaluating the quality and deceptiveness of deepfakes which can be used for predicting the influence of deepfakes on Internet, and it also has potentials in improving the deepfake generation process by serving as a critic. This paper prompts this new direction by presenting a comprehensive benchmark called DREAM, which stands for Deepfake REalism AssessMent. It is comprised of a deepfake video dataset of diverse quality, a large scale annotation that includes 140,000 realism scores and textual descriptions obtained from 3,500 human annotators, and a comprehensive evaluation and analysis of 16 representative realism assessment methods, including recent large vision language model based methods and a newly proposed description-aligned CLIP method. The benchmark and insights included in this study can lay the foundation for future research in this direction and other related areas.

Related papers

• Comparative Analysis of Deepfake Detection Models: New Approaches and Perspectives [0.0]
  This work investigates and compares different approaches for identifying deepfakes, focusing on the GenConViT model.<n>To contextualize the research, the social and legal impacts of deepfakes are addressed, as well as the technical fundamentals of their creation and detection.<n>The obtained results indicated that GenConViT, after fine-tuning, exhibited superior performance in terms of accuracy (93.82%) and generalization capacity.
  arXiv  Detail & Related papers  (2025-04-03T02:10:27Z)
• Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook [101.30779332427217]
  We survey deepfake generation and detection techniques, including the most recent developments in the field.<n>We identify various kinds of deepfakes, according to the procedure used to alter or generate the fake content.<n>We develop a novel multimodal benchmark to evaluate deepfake detectors on out-of-distribution content.
  arXiv  Detail & Related papers  (2024-11-29T08:29:25Z)
• Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights [49.81915942821647]
  Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. This paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity.
  arXiv  Detail & Related papers  (2024-11-12T09:02:11Z)
• Deep Learning Technology for Face Forgery Detection: A Survey [17.519617618071003]
  Deep learning has enabled the creation or manipulation of high-fidelity facial images and videos. This technology, also known as deepfake, has achieved dramatic progress and become increasingly popular in social media. To diminish the risks of deepfake, it is desirable to develop powerful forgery detection methods.
  arXiv  Detail & Related papers  (2024-09-22T01:42:01Z)
• Deepfake Media Forensics: State of the Art and Challenges Ahead [51.33414186878676]
  AI-generated synthetic media, also called Deepfakes, have influenced so many domains, from entertainment to cybersecurity. Deepfake detection has become a vital area of research, focusing on identifying subtle inconsistencies and artifacts with machine learning techniques. This paper reviews the primary algorithms that address these challenges, examining their advantages, limitations, and future prospects.
  arXiv  Detail & Related papers  (2024-08-01T08:57:47Z)
• Linguistic Profiling of Deepfakes: An Open Database for Next-Generation Deepfake Detection [40.20982463380279]
  This paper introduces a deepfake database (DFLIP-3K) for the development of convincing and explainable deepfake detection. It encompasses about 300K diverse deepfake samples from approximately 3K generative models, which boasts the largest number of deepfake models in the literature. The two distinguished features enable DFLIP-3K to develop a benchmark that promotes progress in linguistic profiling of deepfakes.
  arXiv  Detail & Related papers  (2024-01-04T16:19:52Z)
• CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition [53.860796916196634]
  We propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF) Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. It adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination.
  arXiv  Detail & Related papers  (2023-09-30T12:30:25Z)
• Leveraging Deep Learning Approaches for Deepfake Detection: A Review [0.0]
  Deepfakes are fabricated media generated by AI that are difficult to set apart from the real media. This paper aims to explore different methodologies with an intention to achieve a cost-effective model.
  arXiv  Detail & Related papers  (2023-04-04T16:04:42Z)
• A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials [97.69553832500547]
  This paper suggests a continual deepfake detection benchmark (CDDB) over a new collection of deepfakes from both known and unknown generative models. We exploit multiple approaches to adapt multiclass incremental learning methods, commonly used in the continual visual recognition, to the continual deepfake detection problem.
  arXiv  Detail & Related papers  (2022-05-11T13:07:19Z)
• DeepFake Detection with Inconsistent Head Poses: Reproducibility and Analysis [0.0]
  We analyze an existing DeepFake detection technique based on head pose estimation. Our results correct the current literature's perception of state of the art performance for DeepFake detection.
  arXiv  Detail & Related papers  (2021-08-28T22:56:09Z)
• WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection [82.42495493102805]
  We introduce a new dataset WildDeepfake which consists of 7,314 face sequences extracted from 707 deepfake videos collected completely from the internet. We conduct a systematic evaluation of a set of baseline detection networks on both existing and our WildDeepfake datasets, and show that WildDeepfake is indeed a more challenging dataset, where the detection performance can decrease drastically.
  arXiv  Detail & Related papers  (2021-01-05T11:10:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.