Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection

• URL: http://arxiv.org/abs/2404.18649v1
• Date: Mon, 29 Apr 2024 12:32:14 GMT
• Title: Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection
• Authors: Konstantinos Tsigos, Evlampios Apostolidis, Spyridon Baxevanakis, Symeon Papadopoulos, Vasileios Mezaris,
• Abstract summary: This framework assesses the ability of an explanation method to spot the regions of a fake image with the biggest influence on the decision of the deepfake detector. We conduct a comparative study using a state-of-the-art model for deepfake detection that has been trained on the FaceForensics++ dataset.
• Score: 12.179602756337818
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper we propose a new framework for evaluating the performance of explanation methods on the decisions of a deepfake detector. This framework assesses the ability of an explanation method to spot the regions of a fake image with the biggest influence on the decision of the deepfake detector, by examining the extent to which these regions can be modified through a set of adversarial attacks, in order to flip the detector's prediction or reduce its initial prediction; we anticipate a larger drop in deepfake detection accuracy and prediction, for methods that spot these regions more accurately. Based on this framework, we conduct a comparative study using a state-of-the-art model for deepfake detection that has been trained on the FaceForensics++ dataset, and five explanation methods from the literature. The findings of our quantitative and qualitative evaluations document the advanced performance of the LIME explanation method against the other compared ones, and indicate this method as the most appropriate for explaining the decisions of the utilized deepfake detector.

Related papers

• Facial Forgery-based Deepfake Detection using Fine-Grained Features [7.378937711027777]
  Facial forgery by deepfakes has caused major security risks and raised severe societal concerns. We formulate deepfake detection as a fine-grained classification problem and propose a new fine-grained solution to it. Our method is based on learning subtle and generalizable features by effectively suppressing background noise and learning discriminative features at various scales for deepfake detection.
  arXiv  Detail & Related papers  (2023-10-10T21:30:05Z)
• CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition [53.860796916196634]
  We propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF) Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. It adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination.
  arXiv  Detail & Related papers  (2023-09-30T12:30:25Z)
• Towards Generalizable Deepfake Detection by Primary Region Regularization [52.41801719896089]
  This paper enhances the generalization capability from a novel regularization perspective. Our method consists of two stages, namely the static localization for primary region maps, and the dynamic exploitation of primary region masks. We conduct extensive experiments over three widely used deepfake datasets - DFDC, DF-1.0, and Celeb-DF with five backbones.
  arXiv  Detail & Related papers  (2023-07-24T05:43:34Z)
• Beyond AUROC & co. for evaluating out-of-distribution detection performance [50.88341818412508]
  Given their relevance for safe(r) AI, it is important to examine whether the basis for comparing OOD detection methods is consistent with practical needs. We propose a new metric - Area Under the Threshold Curve (AUTC), which explicitly penalizes poor separation between ID and OOD samples.
  arXiv  Detail & Related papers  (2023-06-26T12:51:32Z)
• Assessment Framework for Deepfake Detection in Real-world Situations [13.334500258498798]
  Deep learning-based deepfake detection methods have exhibited remarkable performance. The impact of various image and video processing operations and typical workflow distortions on detection accuracy has not been systematically measured. A more reliable assessment framework is proposed to evaluate the performance of learning-based deepfake detectors in more realistic settings.
  arXiv  Detail & Related papers  (2023-04-12T19:09:22Z)
• Impact of Video Processing Operations in Deepfake Detection [13.334500258498798]
  Digital face manipulation in video has attracted extensive attention due to the increased risk to public trust. Deep learning-based deepfake detection methods have been developed and have shown impressive results. The performance of these detectors is often evaluated using benchmarks that hardly reflect real-world situations.
  arXiv  Detail & Related papers  (2023-03-30T09:24:17Z)
• Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
  arXiv  Detail & Related papers  (2023-03-21T14:24:58Z)
• Towards Better Understanding Attribution Methods [77.1487219861185]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We also propose a post-processing smoothing step that significantly improves the performance of some attribution methods.
  arXiv  Detail & Related papers  (2022-05-20T20:50:17Z)
• Impact of Benign Modifications on Discriminative Performance of Deepfake Detectors [11.881119750753648]
  A large number of deepfake detectors have been proposed recently in order to identify such content. Deepfakes are increasingly popular in both good faith applications such as in entertainment and maliciously intended manipulations such as in image and video forgery. This paper proposes a more rigorous and systematic framework to assess the performance of deepfake detectors in more realistic situations.
  arXiv  Detail & Related papers  (2021-11-14T22:50:39Z)
• Representative Forgery Mining for Fake Face Detection [52.896286647898386]
  We propose an attention-based data augmentation framework to guide detector refine and enlarge its attention. Our method tracks and occludes the Top-N sensitive facial regions, encouraging the detector to mine deeper into the regions ignored before for more representative forgery.
  arXiv  Detail & Related papers  (2021-04-14T03:24:19Z)

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.