Recent improvements in generative AI made synthesizing fake images easy; as
they can be used to cause harm, it is crucial to develop accurate techniques to
identify them. This paper introduces "Locally Aware Deepfake Detection
Algorithm" (LaDeDa), that accepts a single 9x9 image patch and outputs its
deepfake score. The image deepfake score is the pooled score of its patches.
With merely patch-level information, LaDeDa significantly improves over the
state-of-the-art, achieving around 99% mAP on current benchmarks. Owing to the
patch-level structure of LaDeDa, we hypothesize that the generation artifacts
can be detected by a simple model. We therefore distill LaDeDa into
Tiny-LaDeDa, a highly efficient model consisting of only 4 convolutional
layers. Remarkably, Tiny-LaDeDa has 375x fewer FLOPs and is 10,000x more
parameter-efficient than LaDeDa, allowing it to run efficiently on edge devices
with a minor decrease in accuracy. These almost-perfect scores raise the
question: is the task of deepfake detection close to being solved? Perhaps
surprisingly, our investigation reveals that current training protocols prevent
methods from generalizing to real-world deepfakes extracted from social media.
To address this issue, we introduce WildRF, a new deepfake detection dataset
curated from several popular social networks. Our method achieves the top
performance of 93.7% mAP on WildRF, however the large gap from perfect accuracy
shows that reliable real-world deepfake detection is still unsolved.

该研究论文介绍了 “局部感知深度伪造检测算法”（LaDeDa），该算法使用单个 9x9 图像块作为输入，并输出其深度伪造得分。利用图像块级别的信息，LaDeDa 显著提高了检测的准确性，在当前基准测试中达到了约 99% 的平均准确率。此外，通过将 LaDeDa 简化为只有 4 层卷积层的高效模型 Tiny-LaDeDa，实现了 375 倍的浮点运算降低和 10000 倍的参数效率提高，使其可以在边缘设备上高效运行，并在准确性略微下降的情况下获得令人瞩目的成绩。然而，实验发现当前训练协议存在问题，导致方法无法推广到从社交媒体上提取的真实世界深度伪造图像。为解决这一问题，研究引入了一个新的深度伪造检测数据集 WildRF，该方法在该数据集上实现了 93.7% 的最佳性能，然而与完美准确度之间存在较大差距，表明可靠的真实世界深度伪造检测问题仍未解决。