研究人员开发了一个新的框架，以提高深度伪造检测在真实世界图像退化下的鲁棒性。他们的方法集成了极端复合退化引擎和多流架构，优化了DINOv2-Giant骨干网络以提取不变的几何和语义先验。该方法在NTIRE 2026鲁棒性深度伪造检测挑战赛中获得第四名，它使用专门的纹理、面部特征和语义融合流，聚合预测以稳定注意力并很好地泛化到未见过的数据。 AI
影响 增强了深度伪造检测在常见图像退化下的鲁棒性，提高了实际应用能力。
排序理由 这是一篇研究论文，详细介绍了一种新的深度伪造检测方法，并报告了挑战赛的结果。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2604.26453v1 Announce Type: new Abstract: Audio-visual deepfakes have reached a level of realism that makes perceptual detection unreliable, threatening media integrity and biometric security. While multimodal detection has shown promise, most approaches are binary classifi…
Audio-visual deepfakes have reached a level of realism that makes perceptual detection unreliable, threatening media integrity and biometric security. While multimodal detection has shown promise, most approaches are binary classification tasks that often latch onto dataset-speci…
arXiv:2604.25889v1 Announce Type: new Abstract: Current deepfake detection models achieve state-of-the-art performance on pristine academic datasets but suffer severe spatial attention drift under real-world compound degradations, such as blurring and severe lossy compression. To…
Current deepfake detection models achieve state-of-the-art performance on pristine academic datasets but suffer severe spatial attention drift under real-world compound degradations, such as blurring and severe lossy compression. To address this vulnerability, we propose a founda…
arXiv:2604.24163v1 Announce Type: new Abstract: Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight image degradation. In addition to weaker degradations th…
Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight image degradation. In addition to weaker degradations that can accidentally occur in the image processin…