In the last years, lots of approaches devoted to recognize fake images have been developed. Some of them, exploiting traces left in the frequency domain by the fake image generators, were able to achieve satisfactory results also employing simple classifiers. In this paper, a novel white-box evasion attack was introduced to deceive a specific class of frequency-based deepfake detectors exploiting DCT (Discrete Cosine Transform) features. Specifically, statistics computed from the distribution of the AC frequencies computed from fake images are aligned to the corresponding values extracted from authentic images. The robustness of both classical and state-of-the-art DCT-based classifiers has been tested with respect to the proposed attack considering fake images generated by Generative Adversarial Networks and Diffusion Models.

Evasion Attack on Deepfake Detection via DCT Trace Manipulation

Luca Guarnera
;
Francesco Guarnera;Alessandro Ortis;Sebastiano Battiato;
2025-01-01

Abstract

In the last years, lots of approaches devoted to recognize fake images have been developed. Some of them, exploiting traces left in the frequency domain by the fake image generators, were able to achieve satisfactory results also employing simple classifiers. In this paper, a novel white-box evasion attack was introduced to deceive a specific class of frequency-based deepfake detectors exploiting DCT (Discrete Cosine Transform) features. Specifically, statistics computed from the distribution of the AC frequencies computed from fake images are aligned to the corresponding values extracted from authentic images. The robustness of both classical and state-of-the-art DCT-based classifiers has been tested with respect to the proposed attack considering fake images generated by Generative Adversarial Networks and Diffusion Models.
2025
9783031882227
9783031882234
Adversarial discriminator
Adversarial imaging
DCT analysis
Fake images
Withe-box attack
File in questo prodotto:
File Dimensione Formato  
MMFORWILD_2024.pdf

solo gestori archivio

Tipologia: Documento in Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 7.26 MB
Formato Adobe PDF
7.26 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/672689
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact