LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation
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.
Code (1)
Tasks
Language ModelingLanguage ModellingLarge Language Modeltext-to-speechText to SpeechVoice CloningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models
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 DetectionAn End-to-End Multi-Module Audio Deepfake Generation System for ADD Challenge 2023
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 SwappingBts-e: Audio deepfake detection using breathing-talking-silence encoder
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+3Enhancing Fake News Video Detection via LLM-Driven Creative Process Simulation
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 LearningAUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds
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