Papers with Code 아카이브

DeepFake Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 11
보존된 평가 기록: 30

DeepFake Detection is the task of detecting fake videos or images that have been generated using deep learning techniques. Deepfakes are created by using machine learning algorithms to manipulate or replace parts of an original video or image, such as the face of a person. The goal of deepfake detection is to identify such manipulations and distinguish them from real videos or images.

Description source: DeepFakes: a New Threat to Face Recognition? Assessment and Detection

Image source: DeepFakes: a New Threat to Face Recognition? Assessment and Detection

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/10ring/laa-net

공식 코드

LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection

https://github.com/AntonFirc/diffusion-deepfake-speech-dataset

공식 코드

Diffuse or Confuse: A Diffusion Deepfake Speech Dataset

https://github.com/Ashigarg123/ShiftySpeech

공식 코드

ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts

https://github.com/ChenqiKONG/OSDFD

공식 코드

Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture

https://github.com/Clench/TAR_resAE

공식 코드

TAR: Generalized Forensic Framework to Detect Deepfakes using Weakly Supervised Learning

https://github.com/CompVis/taming-transformers

공식 코드

Taming Transformers for High-Resolution Image Synthesis

https://github.com/ControlNet/LAV-DF

공식 코드

Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization

https://github.com/ControlNet/MARLIN

공식 코드

MARLIN: Masked Autoencoder for facial video Representation LearnINg

https://github.com/Coral79/CDDB

공식 코드

A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials

https://github.com/DariusAf/MesoNet

공식 코드

MesoNet: a Compact Facial Video Forgery Detection Network

https://github.com/HuSTeP-Human-Speech-Text-Processing-Lab/XLSR-GRKAN-Conformer

공식 코드

Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models

https://github.com/IDT-ITI/Adv-XAI-Deepfakes

공식 코드

Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples

https://github.com/Jessegator/Audio_robustness_evaluation

공식 코드

Measuring the Robustness of Audio Deepfake Detectors

https://github.com/KamruzzamanAsif/BanglaFake

공식 코드

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset

https://github.com/Leminhbinh0209/AAAI22-ADD

공식 코드

ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images

https://github.com/LetterLiGo/SafeEar

공식 코드

SafeEar: Content Privacy-Preserving Audio Deepfake Detection

https://github.com/MZMMSEC/SJEDD

공식 코드

Semantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approach

https://github.com/NetaGlazer/ADD-GP

공식 코드

Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes

https://github.com/NickyFot/HitchhikersGuide

공식 코드

A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning

https://github.com/OpenRL-Lab/DeepFakeFace

공식 코드

Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models

https://github.com/OpenTAI/wild-deepfake

공식 코드

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection

https://github.com/PalomaCantero/Deepfake-Detection-and-the-Impact-of-Limited-Computing-Capabilities

공식 코드

Deepfake Detection and the Impact of Limited Computing Capabilities

https://github.com/TencentYoutuResearch/OpenWorld-DeepFakeAttribution

공식 코드

Contrastive Pseudo Learning for Open-World DeepFake Attribution

https://github.com/YZY-stack/DF40

공식 코드

DF40: Toward Next-Generation Deepfake Detection

https://github.com/Yuto-Matsunaga/Prompt_Tuning_for_Audio_Deepfake_Detection

공식 코드

Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset

https://github.com/aakash4305/gbdf

공식 코드

GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detection

https://github.com/aaroncomo/lipfd

공식 코드

Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes

https://github.com/abhinavdhall/deepfake

공식 코드

Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization

https://github.com/adipiz99/RawNetLite

공식 코드

End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation

https://github.com/adrianastan/tada

공식 코드

TADA: Training-free Attribution and Out-of-Domain Detection of Audio Deepfakes

https://github.com/ah651/deepfake_adv

공식 코드

Deepfake Forensics via An Adversarial Game

https://github.com/ahaliassos/RealForensics

공식 코드

Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection

https://github.com/ahaliassos/lipforensics

공식 코드

Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection

https://github.com/ai-s2-lab/m2s-add

공식 코드

Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion

https://github.com/aimagelab/COCOFake

공식 코드

Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images

https://github.com/aimagelab/code

공식 코드

Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.