SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Baser, Oguzhan, Kale, Kaan, Chinchali, Sandeep P.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917794089533440
author Baser, Oguzhan
Kale, Kaan
Chinchali, Sandeep P.
author_facet Baser, Oguzhan
Kale, Kaan
Chinchali, Sandeep P.
contents Advancements in DeepFake (DF) audio models pose a significant threat to voice authentication systems, leading to unauthorized access and the spread of misinformation. We introduce a defense mechanism, SecureSpectra, addressing DF threats by embedding orthogonal, irreversible signatures within audio. SecureSpectra leverages the inability of DF models to replicate high-frequency content, which we empirically identify across diverse datasets and DF models. Integrating differential privacy into the pipeline protects signatures from reverse engineering and strikes a delicate balance between enhanced security and minimal performance compromises. Our evaluations on Mozilla Common Voice, LibriSpeech, and VoxCeleb datasets showcase SecureSpectra's superior performance, outperforming recent works by up to 71% in detection accuracy. We open-source SecureSpectra to benefit the research community.
format Preprint
id arxiv_https___arxiv_org_abs_2407_00913
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures
Baser, Oguzhan
Kale, Kaan
Chinchali, Sandeep P.
Cryptography and Security
Machine Learning
Sound
Audio and Speech Processing
Advancements in DeepFake (DF) audio models pose a significant threat to voice authentication systems, leading to unauthorized access and the spread of misinformation. We introduce a defense mechanism, SecureSpectra, addressing DF threats by embedding orthogonal, irreversible signatures within audio. SecureSpectra leverages the inability of DF models to replicate high-frequency content, which we empirically identify across diverse datasets and DF models. Integrating differential privacy into the pipeline protects signatures from reverse engineering and strikes a delicate balance between enhanced security and minimal performance compromises. Our evaluations on Mozilla Common Voice, LibriSpeech, and VoxCeleb datasets showcase SecureSpectra's superior performance, outperforming recent works by up to 71% in detection accuracy. We open-source SecureSpectra to benefit the research community.
title SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures
topic Cryptography and Security
Machine Learning
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2407.00913