As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors as black boxes, while the latent forgery-discriminative knowledge inside them remains largely unexplored. Instead of continuing to rely on resource-intensive full-model retraining to steadily improve detection performance, we ask whether video forgery detection can also be achieved by uncovering and activating sparse forensic knowledge within the detector. We find that forgery-discriminative knowledge is not uniformly distributed across the full representation space, but is concentrated in a sparse set of functionally specialized neurons. Based on this insight, we propose a video forgery-intrinsic neuron discovery (V-FIND) framework. V-FIND first localizes critical layers that exhibit pronounced discrepancies between real and forged videos, and then identifies latent anchor neurons that consistently carry forgery-discriminative signals, organizing them into a compact forensic subspace. With the original backbone frozen and only a lightweight linear classifier trained, this subspace still delivers strong detection performance across multiple external benchmarks for generated videos. Further neuron intervention experiments provide direct evidence for the functional specificity of the discovered neurons. Overall, these results suggest that video forgery detectors contain sparse, extractable, and reusable forgery-discriminative knowledge, offering a new perspective on understanding and exploiting their intrinsic forensic capability.
A generative detector that localizes tampering by estimating the local restoration cost required to align a query image with authentic visual-text statistics, rather than by learning forgery-specific decision boundaries is proposed, and Sparse-Constraint Rectified Flow is introduced, a detector-oriented adaptation of Flow Matching for spatially sparse anomaly localization.
Jiangling Zhang, Shuxuan Gao, Zeyu Chen et al.· 0 citations
Face forgery detection is crucial for preserving the security and integrity of facial data given the rapid developments in face manipulation techniques and deep generative models. Existing methods for video face forgery detection typically assume that all frames in a forged video are manipulated, while detecting partially forged videos that contain only a subset of altered frames remains challenging. To address this issue, we propose a novel framework, UVIF, that utilizes additional annotated images to provide fine-grained supervision for detecting partial forgeries in videos. UVIF employs a unified encoder and a multi-task learning paradigm to jointly model facial videos and images for boosted video face forgery detection. A 2D backbone with temporal fusion modules is employed as the unified encoder. A pseudo labeling process is designed for video frames to bridge their representations with those of static images. A video-oriented feature alignment strategy is further introduced to reduce the distribution gap between videos and images. Extensive experiments on benchmark datasets demonstrate the effectiveness of our framework, which outperforms state-of-theart methods in detecting partially forged videos while introducing no additional computational overhead. Our code is available at https://github.com/haotianll/UVIF.
Haotian Liu, Y. Liu, Guoying Zhao et al.· 0 citations
Generalizable face forgery detection has become a critical problem in multimedia forensics as modern face manipulation techniques can generate increasingly realistic facial content. Vision foundation models provide a promising basis for this problem, but existing detectors usually rely on the last-layer visual feature, implicitly assuming that the most transferable forgery evidence is concentrated in the final representation. In a vision transformer, different layers preserve different visual properties, and face manipulation traces may appear as local texture defects, region-level structural conflicts, or high-level semantic inconsistencies. We revisit CLIP from a hierarchical perspective and propose HIAF, a Hierarchical Interaction and Adaptive Fusion framework for face forgery detection. HIAF extracts representations from multiple transformer depths and learns to use them through two dedicated modules. Cross-Layer Feature Interaction (CFI) performs a bottleneck self-attention along the layer dimension, enabling each layer to absorb complementary evidence from other depths and exposing cross-level inconsistencies that are informative for forgery detection. Layer-aware Adaptive Fusion (LAF) then assigns dynamic weights to different layers, adaptively promoting the layers whose forensic cues are most reliable while suppressing less discriminative ones. To further stabilize the layer-wise feature spaces, we introduce a multi-view contrastive objective that treats each layer as an independent view and regularizes real samples into compact manifolds. Extensive experiments show that HIAF achieves an average AUC of 88.93% in cross-dataset evaluation and 96.54% in cross-manipulation evaluation, outperforming recent state-of-the-art methods.
Yi-Meng Zhao, Shuo Zhu, Jia-Lang Liu et al.· 2026 12th International Conf...· 0 citations
Video forgeries are more threatening and become a serious challenge for digital forensics. Multi-type of video forgeries with the help of AI is more challenging in digital trust and forensics. Deep learning models can expose and classify manipulated videos with high accuracy and efficiency. But, they rarely explain their decisions in applications like courtrooms, media investigations and legal proceedings. This paper presents XAI-VFF, a unified Explainable AI framework that combines Gradient-weighted Class Activation Mapping (Grad-CAM), SHapley Additive exPlanations (SHAP), and Local Interpretable Model-Agnostic Explanations (LIME) for video forgery explanations. This developed with the intention to produce pixel-precise, forensically admissible explanations for multi-type video forgeries at both inter-frame and intra-frame levels. A novel metric, the Forensic Explanation Coverage Score (FECS), is introduced to quantify explanation quality. Experiments on FaceForensics++, DFDC, Celeb-DF v2, and SYSU-OBJFORG show that XAI-VFF achieves a mean FECS of 0.847, Grad-CAM IoU of 0.794, and LIME fidelity of 0.891 across five forgery categories. The framework gives explanations on multi-type video forgeries with no hallucination risk, making it practical for real forensic workflows.
S. P, R. Priya· International journal of com...· 0 citations
This paper proposes an end-to-end Transformer-based framework, termed Progressively Explicit Query Network (PEQNet), for multi-face forgery detection and localization, and introduces triple contrastive learning to model the mutual exclusivity among real, fake, and background regions.
Pengwen Dai, Xiaomeng Wen, Feiyang He et al.· ACM Transactions on Multimed...· 0 citations
This work explores an approach that integrates wavelet-based frequency analysis with deep learning to enhance deepfake detection, and suggests that wavelet sub-bands expose manipulation cues that are useful for detecting unseen fake classes, but they should not be interpreted as a uniform robustness improvement.
