paper-with-me

Papers

What's wrong with this video? Comparing Explainers for Deepfake Detection

2021-05-12 · Samuele Pino, Mark James Carman, Paolo Bestagini

Deepfakes are computer manipulated videos where the face of an individual has been replaced with that of another. Software for creating such forgeries is easy to use and ever more popular, causing serious threats to personal reputation and public security. The quality of classifiers for detecting deepfakes has improved with the releasing of ever larger datasets, but the understanding of why a particular video has been labelled as fake has not kept pace. In this work we develop, extend and compare white-box, black-box and model-specific techniques for explaining the labelling of real and fake videos. In particular, we adapt SHAP, GradCAM and self-attention models to the task of explaining the predictions of state-of-the-art detectors based on EfficientNet, trained on the Deepfake Detection Challenge (DFDC) dataset. We compare the obtained explanations, proposing metrics to quantify their visual features and desirable characteristics, and also perform a user survey collecting users' opinions regarding the usefulness of the explainers.

📄 PDF Abstract BibTeX arXiv:2105.05902

Code (0)

등록된 구현이 없습니다.

Tasks

DeepFake DetectionFace Swapping

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
Sigmoid Activation 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Average Pooling 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Deepfakes at Face Value: Image and Authority

2026-04-14 · James Ravi Kirkpatrick arxiv

Deepfakes are synthetic media that superimpose or generate someone's likeness on to pre-existing sound, images, or videos using deep learning methods. Existing accounts of the wrongs involved in creating and distributing…

What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations

2026-06-24 · Samuel Pagon, Yixuan Shen, Vishal Asnani, Feng Liu arxiv

As deepfake generators approach perceptual indistinguishability, reliable detection becomes critical. Yet, detectors that score well on benchmarks routinely fail in the wild. A concerning feedback loop has emerged: bench…

DeepFake Detection

In Anticipation of Perfect Deepfake: Identity-anchored Artifact-agnostic Detection under Rebalanced Deepfake Detection Protocol

2024-05-01 · Wei-Han Wang, Chin-Yuan Yeh, Hsi-Wen Chen, De-Nian Yang 외

As deep generative models advance, we anticipate deepfakes achieving "perfection"-generating no discernible artifacts or noise. However, current deepfake detectors, intentionally or inadvertently, rely on such artifacts …

DeepFake DetectionFace Swapping

Deep Insights of Deepfake Technology : A Review

2021-05-01 · Bahar Uddin Mahmud, Afsana Sharmin

Under the aegis of computer vision and deep learning technology, a new emerging techniques has introduced that anyone can make highly realistic but fake videos, images even can manipulates the voices. This technology is …

ArticlesFace SwappingMisinformation

Cost Sensitive Optimization of Deepfake Detector

2020-12-08 · Ivan Kukanov, Janne Karttunen, Hannu Sillanpää, Ville Hautamäki

Since the invention of cinema, the manipulated videos have existed. But generating manipulated videos that can fool the viewer has been a time-consuming endeavor. With the dramatic improvements in the deep generative mod…

DeepFake DetectionFace Swapping