Real is not True: Backdoor Attacks Against Deepfake Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Hong, Li, Ziqiang, Liu, Lei, Li, Bin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929271455350784
author Sun, Hong
Li, Ziqiang
Liu, Lei
Li, Bin
author_facet Sun, Hong
Li, Ziqiang
Liu, Lei
Li, Bin
contents The proliferation of malicious deepfake applications has ignited substantial public apprehension, casting a shadow of doubt upon the integrity of digital media. Despite the development of proficient deepfake detection mechanisms, they persistently demonstrate pronounced vulnerability to an array of attacks. It is noteworthy that the pre-existing repertoire of attacks predominantly comprises adversarial example attack, predominantly manifesting during the testing phase. In the present study, we introduce a pioneering paradigm denominated as Bad-Deepfake, which represents a novel foray into the realm of backdoor attacks levied against deepfake detectors. Our approach hinges upon the strategic manipulation of a delimited subset of the training data, enabling us to wield disproportionate influence over the operational characteristics of a trained model. This manipulation leverages inherent frailties inherent to deepfake detectors, affording us the capacity to engineer triggers and judiciously select the most efficacious samples for the construction of the poisoned set. Through the synergistic amalgamation of these sophisticated techniques, we achieve an remarkable performance-a 100% attack success rate (ASR) against extensively employed deepfake detectors.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06610
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Real is not True: Backdoor Attacks Against Deepfake Detection
Sun, Hong
Li, Ziqiang
Liu, Lei
Li, Bin
Cryptography and Security
The proliferation of malicious deepfake applications has ignited substantial public apprehension, casting a shadow of doubt upon the integrity of digital media. Despite the development of proficient deepfake detection mechanisms, they persistently demonstrate pronounced vulnerability to an array of attacks. It is noteworthy that the pre-existing repertoire of attacks predominantly comprises adversarial example attack, predominantly manifesting during the testing phase. In the present study, we introduce a pioneering paradigm denominated as Bad-Deepfake, which represents a novel foray into the realm of backdoor attacks levied against deepfake detectors. Our approach hinges upon the strategic manipulation of a delimited subset of the training data, enabling us to wield disproportionate influence over the operational characteristics of a trained model. This manipulation leverages inherent frailties inherent to deepfake detectors, affording us the capacity to engineer triggers and judiciously select the most efficacious samples for the construction of the poisoned set. Through the synergistic amalgamation of these sophisticated techniques, we achieve an remarkable performance-a 100% attack success rate (ASR) against extensively employed deepfake detectors.
title Real is not True: Backdoor Attacks Against Deepfake Detection
topic Cryptography and Security
url https://arxiv.org/abs/2403.06610