10 papers
Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models
Jianwei Fei, Yunshu Dai, Zhihua Xia +4
Model fingerprinting, embedding user-specific identifiers (fingerprints) into generated outputs, has recently emerged as a popular solution to protect the intellectual property rig…
PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection
Xiaoyu Zhou, Jianwei Fei, Peipeng Yu +3
The rapid evolution of generative AI, from GANs to modern diffusion models, has resulted in increasingly subtle discriminative clues. These fine-grained signals are often overshado…
ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
Junyan Luo, Peipeng Yu, Jianwei Fei +4
Deepfake technologies have rapidly advanced with modern generative AI, and face swapping in particular poses serious threats to privacy and digital security. Existing proactive def…
Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images
JinFeng Xie, Chengfu Ou, Peipeng Yu +5
The rapid adoption of diffusion-based generative models has intensified concerns over the attribution and integrity of AI-generated content (AIGC). Existing single-domain watermark…
LBFTI: Layer-Based Facial Template Inversion for Identity-Preserving Fine-Grained Face Reconstruction
Zixuan Shen, Zhihua Xia, Kaikai Gan +1
In face recognition systems, facial templates are widely adopted for identity authentication due to their compliance with the data minimization principle. However, facial template…
High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking
Peipeng Yu, Jinfeng Xie, Chengfu Ou +5
The proliferation of AIGC-driven face manipulation and deepfakes poses severe threats to media provenance, integrity, and copyright protection. Existing versatile watermarking syst…
CLIP-FTI: Fine-Grained Face Template Inversion via CLIP-Driven Attribute Conditioning
Longchen Dai, Zixuan Shen, Zhiheng Zhou +2
Face recognition systems store face templates for efficient matching. Once leaked, these templates pose a threat: inverting them can yield photorealistic surrogates that compromise…
Fine-Grained DINO Tuning with Dual Supervision for Face Forgery Detection
Tianxiang Zhang, Peipeng Yu, Zhihua Xia +3
The proliferation of sophisticated deepfakes poses significant threats to information integrity. While DINOv2 shows promise for detection, existing fine-tuning approaches treat it…
Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection
Peipeng Yu, Jianwei Fei, Hui Gao +3
Current Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in understanding multimodal data, but their potential remains underexplored for deepfake dete…
DFREC: DeepFake Identity Recovery Based on Identity-aware Masked Autoencoder
Peipeng Yu, Hui Gao, Jianwei Fei +3
Recent advances in deepfake forensics have primarily focused on improving the classification accuracy and generalization performance. Despite enormous progress in detection accurac…