Papers › Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Method

Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Method

14 May 2024arXiv:2405.08487archive 2025-07-28

Mian Zou, Baosheng Yu, Yibing Zhan, Siwei Lyu, Kede Ma

In recent years, deep learning has greatly streamlined the process of manipulating photographic face images. Aware of the potential dangers, researchers have developed various tools to spot these counterfeits. Yet, none asks the fundamental question: What digital manipulations make a real photographic face image fake, while others do not? In this paper, we put face forgery in a semantic context and define that computational methods that alter semantic face attributes to exceed human discrimination thresholds are sources of face forgery. Following our definition, we construct a large face forgery image dataset, where each image is associated with a set of labels organized in a hierarchical graph. Our dataset enables two new testing protocols to probe the generalizability of face forgery detectors. Moreover, we propose a semantics-oriented face forgery detection method that captures label relations and prioritizes the primary task (i.e., real or fake face detection). We show that the proposed dataset successfully exposes the weaknesses of current detectors as the test set and consistently improves their generalizability as the training set. Additionally, we demonstrate the superiority of our semantics-oriented method over traditional binary and multi-class classification-based detectors.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

MZMMSEC/SO-DFD officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Face DetectionMulti-class Classification

Datasets

Introduced by this paper, per the archive.

FFSC

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AWARESET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections