Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:T56O23BWrecord.jsonopen to challenge →
read the original abstract
The rapid advancement of AI technologies has significantly increased the diversity of DeepFake videos circulating online, posing a pressing challenge for \textit{generalizable forensics}, \ie, detecting a wide range of unseen DeepFake types using a single model. Addressing this challenge requires datasets that are not only large-scale but also rich in forgery diversity. However, most existing datasets, despite their scale, include only a limited variety of forgery types, making them insufficient for developing generalizable detection methods. Therefore, we build upon our earlier Celeb-DF dataset and introduce {Celeb-DF++}, a new large-scale and challenging video DeepFake benchmark dedicated to the generalizable forensics challenge. Celeb-DF++ covers three commonly encountered forgery scenarios: Face-swap (FS), Face-reenactment (FR), and Talking-face (TF). Each scenario contains a substantial number of high-quality forged videos, generated using a total of 22 various recent DeepFake methods. These methods differ in terms of architectures, generation pipelines, and targeted facial regions, covering the most prevalent DeepFake cases witnessed in the wild. We also introduce evaluation protocols for measuring the generalizability of 24 recent detection methods, highlighting the limitations of existing detection methods and the difficulty of our new dataset.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
Detecting Deepfakes via Hamiltonian Dynamics
HAAD detects deepfakes by modeling latent manifolds as potential energy surfaces and quantifying instability via Hamiltonian trajectory statistics such as action and energy dissipation.
-
Energy-Based Constraint Networks: Learning Structural Coherence Across Modalities
Energy-based constraint networks learn structural coherence from contrastive pairs using frozen encoders, achieving 93.4% accuracy on text corruptions and 0.959 AUC on deepfake detection with composable branches that ...
-
What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations
Linear probes on frozen self-supervised representations closely approach bespoke deepfake detector performance on benchmarks, indicating benchmarks largely measure general modality understanding.
-
The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection
Deepfake detectors act as alpha blending searchers; training solely on self-blended real images yields top cross-dataset generalization on 15 datasets without using synthetic deepfakes.
-
SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
SynthForensics is a people-centric benchmark where face-based detectors lose 13-55 AUC points on modern synthetic videos compared to legacy manipulation sets.
-
Deepfake Detection that Generalizes Across Benchmarks
GenD achieves state-of-the-art average cross-dataset AUROC in deepfake detection by parameter-efficient adaptation of a foundational vision encoder with hyperspherical manifold enforcement via L2 normalization and met...
-
PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution
PVLM combines parsing-aware vision-language modeling with dynamic contrastive learning to enable fine-grained zero-shot attribution of deepfakes to unseen generators and outperforms prior methods on a new benchmark.
-
Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake Detection
DiCoME decomposes entangled representations into decorrelated semantic and artifact views using geometric purification and uncertainty-aware evidential learning to improve generalization and produce calibrated uncerta...
-
Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities
Introduces MAF framework and DeepModal-Bench to capture universal cross-modal forgery traces for better generalization in multimodal deepfake detection.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.