paper-with-me

홈 › Papers

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

2024-09-23 · Hieu-Thi Luong, Haoyang Li, Lin Zhang, Kong Aik Lee, Eng Siong Chng

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.

📄 PDF Abstract BibTeX arXiv:2409.14743

Code (1)

hieuthi/llamapartialspoof 공식 구현

Tasks

Language ModelingLanguage ModellingLarge Language Modeltext-to-speechText to SpeechVoice Cloning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models

2026-04-01 · Awais Khan, Muhammad Umar Farooq, Kutub Uddin, Khalid Malik arxiv

Partial audio deepfakes, where synthesized segments are spliced into genuine recordings, are particularly deceptive because most of the audio remains authentic. Existing detectors are supervised: they require frame-level…

Audio Deepfake Detection

An End-to-End Multi-Module Audio Deepfake Generation System for ADD Challenge 2023

2023-07-03 · Sheng Zhao, Qilong Yuan, Yibo Duan, Zhuoyue Chen

The task of synthetic speech generation is to generate language content from a given text, then simulating fake human voice.The key factors that determine the effect of synthetic speech generation mainly include speed of…

Face Swapping

Bts-e: Audio deepfake detection using breathing-talking-silence encoder

2023-05-05 · IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023 5 · Thien-Phuc Doan, Long Nguyen-Vu, Souhwan Jung, Kihun Hong

Voice phishing (vishing) is increasingly popular due to the development of speech synthesis technology. In particular, the use of deep learning to generate an arbitrary-content audio clip simulating the victim’s voice ma…

Audio Deepfake DetectionDeepFake DetectionFace SwappingSpeaker Verification+3

Enhancing Fake News Video Detection via LLM-Driven Creative Process Simulation

2025-10-05 · Yuyan Bu, Qiang Sheng, Juan Cao, Shaofei Wang 외 arxiv

The emergence of fake news on short video platforms has become a new significant societal concern, necessitating automatic video-news-specific detection. Current detectors primarily rely on pattern-based features to sepa…

Data AugmentationActive Learning

AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds

2025-09-04 · Qizhou Wang, Hanxun Huang, Guansong Pang, Sarah Erfani 외 arxiv

Speech synthesis systems can now produce highly realistic vocalisations that pose significant authenticity challenges. Despite substantial progress in deepfake detection models, their real-world effectiveness is often un…

DeepFake DetectionSpeech Synthesis