English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The emergence of text-to-image generative models has revolutionized the fieldof deepfakes, enabling the creation of realistic and convincing visual contentdirectly from textual descriptions. However, this advancement presentsconsiderably greater challenges in detecting the authenticity of such content.Existing deepfake detection datasets and methods often fall short ineffectively capturing the extensive range of emerging deepfakes and offeringsatisfactory explanatory information for detection. To address the significantissue, this paper introduces a deepfake database (DFLIP-3K) for the developmentof convincing and explainable deepfake detection. It encompasses about 300Kdiverse deepfake samples from approximately 3K generative models, which boaststhe largest number of deepfake models in the literature. Moreover, it collectsaround 190K linguistic footprints of these deepfakes. The two distinguishedfeatures enable DFLIP-3K to develop a benchmark that promotes progress inlinguistic profiling of deepfakes, which includes three sub-tasks namelydeepfake detection, model identification, and prompt prediction. The deepfakemodel and prompt are two essential components of each deepfake, and thusdissecting them linguistically allows for an invaluable exploration oftrustworthy and interpretable evidence in deepfake detection, which we believeis the key for the next-generation deepfake detection. Furthermore, DFLIP-3K isenvisioned as an open database that fosters transparency and encouragescollaborative efforts to further enhance its growth. Our extensive experimentson the developed benchmark verify that our DFLIP-3K database is capable ofserving as a standardized resource for evaluating and comparinglinguistic-based deepfake detection, identification, and prompt predictiontechniques.

Linguistic Profiling of Deepfakes: An Open Database for Next-Generation Deepfake Detection