HAAD detects deepfakes by modeling latent manifolds as potential energy surfaces and quantifying instability via Hamiltonian trajectory statistics such as action and energy dissipation.
Celeb-df++: A large-scale chal- lenging video deepfake benchmark for generalizable forensics
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 9roles
dataset 1polarities
use dataset 1representative citing papers
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 transfer across modalities via corruption respecification.
Linear probes on frozen self-supervised representations closely approach bespoke deepfake detector performance on benchmarks, indicating benchmarks largely measure general modality understanding.
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 is a people-centric benchmark where face-based detectors lose 13-55 AUC points on modern synthetic videos compared to legacy manipulation sets.
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 metric learning.
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.
DiCoME decomposes entangled representations into decorrelated semantic and artifact views using geometric purification and uncertainty-aware evidential learning to improve generalization and produce calibrated uncertainty in deepfake detection.
Introduces MAF framework and DeepModal-Bench to capture universal cross-modal forgery traces for better generalization in multimodal deepfake detection.
citing papers explorer
-
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 transfer across modalities via corruption respecification.
-
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 metric learning.
-
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 uncertainty in deepfake detection.
-
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.