LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation

  • Hieu Thi Luong
  • , Haoyang Li
  • , Lin Zhang
  • , Kong Aik Lee
  • , Eng Siong Chng

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Previous fake speech datasets were constructed from a defender's perspective to develop countermeasure (CM) systems without considering diverse motivations of attackers. To better align with real-life scenarios, we created LlamaPartialSpoof, a 130-hour dataset that contains both fully and partially fake speech, using a large language model (LLM) and voice cloning technologies to evaluate the robustness of CMs. By examining valuable information for both attackers and defenders, we identify several key vulnerabilities in current CM systems, which can be exploited to enhance attack success rates, including biases toward certain text-to-speech models or concatenation methods. Our experimental results indicate that the current fake speech detection system struggle to generalize to unseen scenarios, achieving a best performance of 24.49% equal error rate.

Original languageEnglish
Title of host publicationEnglish
Pages1-5
DOIs
Publication statusPublished - Apr 2025
Event2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 - Hyderabad, India
Duration: 6 Apr 202511 Apr 2025

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
ISSN (Print)1520-6149

Conference

Conference2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025
Country/TerritoryIndia
CityHyderabad
Period6/04/2511/04/25

Keywords

  • dataset
  • deepfake
  • fake speech detection
  • large language model
  • voice cloning

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation'. Together they form a unique fingerprint.

Cite this