Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection
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...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.2404.18649 |