Audio-Visual Deepfake Detection With Local Temporal Inconsistencies
- URL: http://arxiv.org/abs/2501.08137v2
- Date: Tue, 28 Jan 2025 09:14:14 GMT
- Title: Audio-Visual Deepfake Detection With Local Temporal Inconsistencies
- Authors: Marcella Astrid, Enjie Ghorbel, Djamila Aouada,
- Abstract summary: This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities.
From an architectural perspective, a temporal distance map, coupled with an attention mechanism, is designed to capture these inconsistencies.
Our approach is evaluated against state-of-the-art methods using the DFDC and FakeAVCeleb datasets.
- Score: 11.671275975119089
- License:
- Abstract: This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities. To achieve this, both architectural and data synthesis strategies are introduced. From an architectural perspective, a temporal distance map, coupled with an attention mechanism, is designed to capture these inconsistencies while minimizing the impact of irrelevant temporal subsequences. Moreover, we explore novel pseudo-fake generation techniques to synthesize local inconsistencies. Our approach is evaluated against state-of-the-art methods using the DFDC and FakeAVCeleb datasets, demonstrating its effectiveness in detecting audio-visual deepfakes.
Related papers
- DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization [13.840950434728533]
We present a novel audio-visual deepfake detection framework.
Based on the assumption that in real samples - in contrast to deepfakes - visual and audio signals coincide in terms of information.
We use features from deep networks that specialize in video and audio speech recognition to spot frame-level cross-modal incongruities.
arXiv Detail & Related papers (2024-11-15T13:47:33Z) - Detecting Audio-Visual Deepfakes with Fine-Grained Inconsistencies [11.671275975119089]
We propose the introduction of fine-grained mechanisms for detecting subtle artifacts in both spatial and temporal domains.
First, we introduce a local audio-visual model capable of capturing small spatial regions that are prone to inconsistencies with audio.
Second, we introduce a temporally-local pseudo-fake augmentation to include samples incorporating subtle temporal inconsistencies in our training set.
arXiv Detail & Related papers (2024-08-13T09:19:59Z) - Statistics-aware Audio-visual Deepfake Detector [11.671275975119089]
Methods in audio-visualfake detection mostly assess the synchronization between audio and visual features.
We propose a statistical feature loss to enhance the discrimination capability of the model.
Experiments on the DFDC and FakeAVCeleb datasets demonstrate the relevance of the proposed method.
arXiv Detail & Related papers (2024-07-16T12:15:41Z) - AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts [8.809586885539002]
We propose a novel approach utilizing audio-visual multimodal data.
This method enhances audio feature extraction by leveraging Mel Frequency Cepstral Coefficients (MFCC) and Log-Mel spectrogram features alongside a pre-trained VGGish network.
Our method notably improves the accuracy of AU detection by understanding the temporal and contextual nuances of the data, showcasing significant advancements in the comprehension of intricate scenarios.
arXiv Detail & Related papers (2024-03-20T15:37:19Z) - An Efficient Temporary Deepfake Location Approach Based Embeddings for
Partially Spoofed Audio Detection [4.055489363682199]
We propose a fine-grained partially spoofed audio detection method, namely Temporal Deepfake Location (TDL)
Our approach involves two novel parts: embedding similarity module and temporal convolution operation.
Our method outperform baseline models in ASVspoof 2019 Partial Spoof dataset and demonstrate superior performance even in the crossdataset scenario.
arXiv Detail & Related papers (2023-09-06T14:29:29Z) - Histogram Layer Time Delay Neural Networks for Passive Sonar
Classification [58.720142291102135]
A novel method combines a time delay neural network and histogram layer to incorporate statistical contexts for improved feature learning and underwater acoustic target classification.
The proposed method outperforms the baseline model, demonstrating the utility in incorporating statistical contexts for passive sonar target recognition.
arXiv Detail & Related papers (2023-07-25T19:47:26Z) - NPVForensics: Jointing Non-critical Phonemes and Visemes for Deepfake
Detection [50.33525966541906]
Existing multimodal detection methods capture audio-visual inconsistencies to expose Deepfake videos.
We propose a novel Deepfake detection method to mine the correlation between Non-critical Phonemes and Visemes, termed NPVForensics.
Our model can be easily adapted to the downstream Deepfake datasets with fine-tuning.
arXiv Detail & Related papers (2023-06-12T06:06:05Z) - Deep Spectro-temporal Artifacts for Detecting Synthesized Speech [57.42110898920759]
This paper provides an overall assessment of track 1 (Low-quality Fake Audio Detection) and track 2 (Partially Fake Audio Detection)
In this paper, spectro-temporal artifacts were detected using raw temporal signals, spectral features, as well as deep embedding features.
We ranked 4th and 5th in track 1 and track 2, respectively.
arXiv Detail & Related papers (2022-10-11T08:31:30Z) - Delving into Sequential Patches for Deepfake Detection [64.19468088546743]
Recent advances in face forgery techniques produce nearly untraceable deepfake videos, which could be leveraged with malicious intentions.
Previous studies has identified the importance of local low-level cues and temporal information in pursuit to generalize well across deepfake methods.
We propose the Local- & Temporal-aware Transformer-based Deepfake Detection framework, which adopts a local-to-global learning protocol.
arXiv Detail & Related papers (2022-07-06T16:46:30Z) - Unsupervised Sound Localization via Iterative Contrastive Learning [106.56167882750792]
We propose an iterative contrastive learning framework that requires no data annotations.
We then use the pseudo-labels to learn the correlation between the visual and audio signals sampled from the same video.
Our iterative strategy gradually encourages the localization of the sounding objects and reduces the correlation between the non-sounding regions and the reference audio.
arXiv Detail & Related papers (2021-04-01T07:48:29Z) - Exploiting Attention-based Sequence-to-Sequence Architectures for Sound
Event Localization [113.19483349876668]
This paper proposes a novel approach to sound event localization by utilizing an attention-based sequence-to-sequence model.
It yields superior localization performance compared to state-of-the-art methods in both anechoic and reverberant conditions.
arXiv Detail & Related papers (2021-02-28T07:52:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.