Generalizable speech deepfake detection via meta-learned LoRA
Generalizable deepfake detection can be formulated as a detection problem where labels (bonafide and fake) are fixed but distributional drift affects the deepfake set. We can always train our detector with one-selected attacks and bonafide data, but an attacker can generate new attacks by just retraining his generator with a different seed. One reasonable approach is to simply pool all different attack types available in training time. Our proposed approach is to utilize meta-learning in combination with LoRA adapters to learn the structure in the training data that is common to all attack types.
Code (0)
등록된 구현이 없습니다.
Tasks
DeepFake DetectionFace SwappingMeta-LearningSimilar Papers 제목 키워드 기반
Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection
Foundation models such as Wav2Vec2 excel at representation learning in speech tasks, including audio deepfake detection. However, after being fine-tuned on a fixed set of bonafide and spoofed audio clips, they often fail…
Audio Deepfake DetectionRepresentation LearningGeneralizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment
Neural speech synthesis techniques have enabled highly realistic speech deepfakes, posing major security risks. Speech deepfake detection is challenging due to distribution shifts across spoofing methods and variability …
DeepFake DetectionSpeech SynthesisAT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan
The rapid advancement of Audio Large Language Models (ALLMs) has enabled cost-effective, high-fidelity generation and manipulation of both speech and non-speech audio, including sound effects, singing voices, and music. …
Audio Deepfake DetectionDo You See What I Say? Generalizable Deepfake Detection based on Visual Speech Recognition
Deepfake generation has witnessed remarkable progress, contributing to highly realistic generated images, videos, and audio. While technically intriguing, such progress has raised serious concerns related to the misuse o…
Visual Speech RecognitionDeepFake DetectionMeta-Learning Approaches for Improving Detection of Unseen Speech Deepfakes
Current speech deepfake detection approaches perform satisfactorily against known adversaries; however, generalization to unseen attacks remains an open challenge. The proliferation of speech deepfakes on social media un…
DeepFake DetectionFace SwappingMeta-Learning