PulseAugur
实时 07:33:11
English(EN) Towards Generalizable Deepfake Image Detection with Vision Transformers

新的基准和Vision Transformer推动深度伪造检测能力发展

研究人员正在开发更鲁棒的深度伪造图像检测方法,以应对当前技术的局限性。一种方法利用了微调的Vision Transformer集成,在DF-Wild数据集上达到了96.77%的AUC和9%的EER,优于现有的最先进算法。同时,引入了一个名为XPlainVerse的新基准,包含一百万张图像,用于评估可解释的深度伪造检测。该基准侧重于自然语言解释的质量和依据性,提出了EntityScore和EvidenceScore等新指标,以评估超越简单分类准确性的推理保真度。 AI

影响 深度伪造检测和可解释性的进步可以增强对数字媒体的信任,并有助于打击虚假信息。

排序理由 两篇arXiv论文介绍了深度伪造检测的新方法和基准。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的基准和Vision Transformer推动深度伪造检测能力发展

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Kaliki V Srinanda, M Manvith Prabhu, Hemanth K Mogilipalem, Jayavarapu S Abhinai, Vaibhav Santhosh, Aryan Herur, Deepu Vijayasenan ·

    Towards Generalizable Deepfake Image Detection with Vision Transformers

    arXiv:2604.17376v2 Announce Type: replace-cross Abstract: In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods. In this paper, we use an ensemb…

  2. arXiv cs.CV TIER_1 English(EN) · Abhijeet Narang, Kartik Kuckreja, Shreya Ghosh, Muhammad Haris Khan, Jianfei Cai, Abhinav Dhall ·

    XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection

    arXiv:2607.03562v1 Announce Type: new Abstract: As deepfake detection models increasingly produce natural language explanations, their reasoning often remains weakly grounded in visual artifacts, limiting reliability and user trust. Existing benchmarks mainly evaluate classificat…