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

• URL: http://arxiv.org/abs/2105.05902v1
• Date: Wed, 12 May 2021 18:44:39 GMT
• Title: What's wrong with this video? Comparing Explainers for Deepfake Detection
• Authors: Samuele Pino, Mark James Carman, Paolo Bestagini
• Abstract summary: Deepfakes are computer manipulated videos where the face of an individual has been replaced with that of another. 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.
• Score: 13.089182408360221
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Deepfake detection in videos with multiple faces using geometric-fakeness features [79.16635054977068]
  Deepfakes of victims or public figures can be used by fraudsters for blackmailing, extorsion and financial fraud. In our research we propose to use geometric-fakeness features (GFF) that characterize a dynamic degree of a face presence in a video. We employ our approach to analyze videos with multiple faces that are simultaneously present in a video.
  arXiv  Detail & Related papers  (2024-10-10T13:10:34Z)
• Shaking the Fake: Detecting Deepfake Videos in Real Time via Active Probes [3.6308756891251392]
  Real-time deepfake, a type of generative AI, is capable of "creating" non-existing contents (e.g., swapping one's face with another) in a video. It has been misused to produce deepfake videos for malicious purposes, including financial scams and political misinformation. We propose SFake, a new real-time deepfake detection method that exploits deepfake models' inability to adapt to physical interference.
  arXiv  Detail & Related papers  (2024-09-17T04:58:30Z)
• Undercover Deepfakes: Detecting Fake Segments in Videos [1.2609216345578933]
  deepfake generation is a new paradigm of deepfakes which are mostly real videos altered slightly to distort the truth. In this paper, we present a deepfake detection method that can address this issue by performing deepfake prediction at the frame and video levels. In particular, the paradigm we address will form a powerful tool for the moderation of deepfakes, where human oversight can be better targeted to the parts of videos suspected of being deepfakes.
  arXiv  Detail & Related papers  (2023-05-11T04:43:10Z)
• Video Manipulations Beyond Faces: A Dataset with Human-Machine Analysis [60.13902294276283]
  We present VideoSham, a dataset consisting of 826 videos (413 real and 413 manipulated). Many of the existing deepfake datasets focus exclusively on two types of facial manipulations -- swapping with a different subject's face or altering the existing face. Our analysis shows that state-of-the-art manipulation detection algorithms only work for a few specific attacks and do not scale well on VideoSham.
  arXiv  Detail & Related papers  (2022-07-26T17:39:04Z)
• Audio-Visual Person-of-Interest DeepFake Detection [77.04789677645682]
  The aim of this work is to propose a deepfake detector that can cope with the wide variety of manipulation methods and scenarios encountered in the real world. We leverage a contrastive learning paradigm to learn the moving-face and audio segment embeddings that are most discriminative for each identity. Our method can detect both single-modality (audio-only, video-only) and multi-modality (audio-video) attacks, and is robust to low-quality or corrupted videos.
  arXiv  Detail & Related papers  (2022-04-06T20:51:40Z)
• Voice-Face Homogeneity Tells Deepfake [56.334968246631725]
  Existing detection approaches contribute to exploring the specific artifacts in deepfake videos. We propose to perform the deepfake detection from an unexplored voice-face matching view. Our model obtains significantly improved performance as compared to other state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-03-04T09:08:50Z)
• Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motion [82.06128362686445]
  We propose a multi-modal semantic forensic approach to handle both cheapfakes and visually persuasive deepfakes. We leverage the idea of attribution to learn person-specific biometric patterns that distinguish a given speaker from others. Unlike existing person-specific approaches, our method is also effective against attacks that focus on lip manipulation.
  arXiv  Detail & Related papers  (2021-12-21T01:57:04Z)
• Detecting Deepfake Videos Using Euler Video Magnification [1.8506048493564673]
  Deepfake videos are manipulating videos using advanced machine learning techniques. In this paper, we examine a technique for possible identification of deepfake videos. Our approach uses features extracted from the Euler technique to train three models to classify counterfeit and unaltered videos.
  arXiv  Detail & Related papers  (2021-01-27T17:37:23Z)
• 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)
• Deepfake Video Forensics based on Transfer Learning [0.0]
  "Deepfake" can create fake images and videos that humans cannot differentiate from the genuine ones. This paper details retraining the image classification models to apprehend the features from each deepfake video frames. When checking Deepfake videos, this technique received more than 87 per cent accuracy.
  arXiv  Detail & Related papers  (2020-04-29T13:21:28Z)

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.