This work proposes a robust, generalizable proactive face-swapping defense via semantic gradient divergence (SGD-Guard), and introduces an integrated feature gallery that uses CLIP features and a generalized identity feature, obtained by iteratively refining heterogeneous identity features into a homogeneous representation.
This work proposes SRAP, which combines per-channel truncated SVD refinement with an identity-importance mask at every optimization step, and demonstrates that SRAP substantially improves protected-image fidelity across all reported metrics while maintaining competitive identity-disruption performance.
The increasing realism of image manipulations poses significant challenges for forgery localization. However, existing methods are hindered by the limited adaptability of constrained frequency filters and the dilution of subtle forensic cues in deep networks. To address these challenges, we propose the Laplacian pyramid reweighting with progressive Residual Learning framework (LapRL-Net). First, a Laplacian Residual Adaptive Reweighting (LRAR) module is introduced to adaptively modulate multi-scale frequency residuals, enabling flexible extraction of discriminative frequency artifacts. Second, to mitigate feature dilution, we design a Progressive global-local Residual Fusion Module (PRFM) with multi-level residual fusion, which progressively combines global contextual dependencies with local texture details to preserve critical forensic cues. Furthermore, an Edge-Guided Refinement Module (EGRM) is incorporated to enhance boundary accuracy by enforcing geometric consistency via edge supervision. Extensive experiments on multiple benchmarks demonstrate that the proposed method achieves competitive performance in complex forensic scenarios.
Zhuo-Fei Liu, Wen-Jie Li, Yang Yu· IEEE Signal Processing Lette...· 0 citations
The rapid advancement of deepfake image generation poses significant threats to information security and social trust, with forgery artifacts exhibiting multi-scale characteristics from micro-level noise to macro-level semantic anomalies.Existing detection methods are limited by single-scale feature extraction and inefficient fusion due to semantic gaps between deep and shallow features.To address these issues, this letter proposes a Progressive Multi-Level Collaborative Framework (PMCF) comprising a multi-granularity collaborative attention (MGCA) module and a multi-level attention fusion (MLAF) module. MGCA uses three parallel Transformer branches to model pixel-level textures, local structures, and global semantics, while MLAF integrates a feature pyramid, joint attention, and progressive bidirectional fusion for effective feature alignment. Experimental results show consistent AUC improvements over comparative methods across multiple datasets.
Hongning Li, Zengzhang Li, Haijie Du et al.· IEEE Signal Processing Lette...· 0 citations
Face forgery detection (FFD) is essential for the security and authenticity verification of digital media. Current FFD methods suffer from poor generalization to unseen face images created by diffusion models. Besides, they tend to rely on coarse-grained prior information interaction paradigms. In this paper, we propose a novel fine-grained identity-aware transformer (FIT) method for generalizable diffusion face forgery detection (DFFD). Specifically, we are motivated by the novel observation that the preservation of target identity in facial images generated by GAN and diffusion models varies significantly. We employ the inherent identity preservation differences between GAN and diffusion face images to capture identity-aware forgery representations in a fine-grained learning manner. We employ the learned identity forgery embeddings as prior information to facilitate DFFD. We propose a fine-grained identity-aware transformer block (FITB) to mine fine-grained global identity-appearance forgery features based on intra-patch identity-aware relations as well as inter-patch global identity-perceptual relationships in diffusion face images. An identity contrastive center loss is devised to achieve intra-class identity forgery embedding compaction and inter-class identity forgery representation separation, to study discriminative and general diffusion face forgery patterns. Extensive experimental results demonstrate that FIT outperforms the state-of-the-art via cross-generator, cross-dataset, and robustness evaluation.
Generative diffusion models have revolutionized facial image synthesis, yet robust identity preservation in high resolution outputs remains a critical challenge. This issue is especially vital for security systems, biometric authentication, and privacy sensitive applications, where any drift in identity integrity can undermine trust and functionality. We introduce Diff-ID, a diffusion based framework that enforces identity consistency while delivering photorealistic quality. Central to our approach is a custom 210K image dataset synthesized from CelebA-HQ, FFHQ, and LAION-Face and captioned via a fine tuned BLIP model to bolster identity awareness during training. Diff-ID integrates ArcFace and CLIP embeddings through a dual cross attention adapter within a fine tuned Stable Diffusion UNet. To further reinforce identity fidelity, we propose a pseudo discriminator loss based on ArcFace cosine similarity with exponential timestep weighting. Experiments on held out and unseen faces show that Diff-ID does not exceed InstantID in raw ArcFace Face Similarity, but achieves substantially lower FID and the strongest FIQ based identity--realism trade off among the evaluated methods. We also present a unified DDIM based morphing pipeline that enables qualitative facial interpolation without per identity fine tuning. We further argue that identity preservation and photorealism should be evaluated jointly rather than in isolation, as high identity similarity alone does not guarantee realistic outputs. To make this trade off explicit, we report Face Image Quality (FIQ) as a complementary ratio based score that combines identity similarity and perceptual realism while keeping FS and FID as the primary metrics.
T. Rizwan, Sara Atito, Muhammad Awais et al.· 0 citations
Morphing attacks pose a serious threat to face recognition systems. However, existing image-based morphing attack detection (MAD) methods often generalize poorly to unseen generation techniques because they rely solely on visual cues. We propose XSA-MAD, a CLIP-based multimodal framework that explicitly models semantic inconsistencies between bona-fide and morphed faces. Morphing concepts are decomposed into four interpretable attributes, including identity, facial geometry, texture, and consistency, and are encoded as structured and attribute-aware textual representations. The image encoder is progressively aligned with this discriminative textual space, resulting in a unified semantic representation that captures generation-invariant and concept-level discrepancies between bona-fide and morph images. Experiments on MAD22 and MorDIFF, following training on SMDD, demonstrate strong generalization across diverse morphing principles. In particular, XSA-MAD achieves an equal error rate of 2.92% on GAN-based morphs and consistently outperforms existing methods under high-fidelity generative attacks.
Jie Jin, Mahiro Tokumasu, Yushi Makino et al.· International Conference on...· 0 citations