15 papers
No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation
Lizhi Xiong, Jun Li, Ziqiang Li +2
Recent advances in diffusion models have enabled high-fidelity, identity-preserving image generation for personalized applications such as digital avatars and virtual try-on system…
Prompt-Segmentation Meets ROI Encryption: Fine-Grained Video Protection Based on Diffusion Isolation
Xiang Zhang, Haoyan Lu, Ziqiang Li +4
Region-of-interest (ROI) selective encryption in H.265/HEVC aims to protect sensitive content while preserving the utility of non-ROI regions. Existing coding-unit (CU)-level appro…
Robust Coverless Linguistic Steganography via Sentence Embedding Space with Global Resynchronization
Lizhi Xiong, Yuping Lu, Jun Li +2
Linguistic steganography enables covert communication through natural language. Existing methods heavily rely on token-level operations and struggle to maintain reliability under w…
Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
Jun Li, Lizhi Xiong, Ziqiang Li +4
Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in larg…
Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
Zida Li, Jun Li, Yuzhe Sha +3
Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor sec…
PhysInOne: Visual Physics Learning and Reasoning in One Suite
Siyuan Zhou, Hejun Wang, Hu Cheng +36
We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to mere…
A H.265/HEVC Fine-Grained ROI Video Encryption Algorithm Based on Coding Unit and Prompt Segmentation
Xiang Zhang, Haoyan Lu, Ziqiang Li +4
ROI (Region of Interest) video selective encryption based on H.265/HEVC is a technology that protects the sensitive regions of videos by perturbing the syntax elements associated w…
A Video Steganography for H.265/HEVC Based on Multiple CU Size and Block Structure Distortion
Xiang Zhang, Wen Jiang, Fei Peng +3
Video steganography based on block structure, which embeds secret information by modifying Coding Unit (CU) block structure of I-frames, is currently a research hotspot. However, t…
Generalizable Deepfake Detection Based on Forgery-aware Layer Masking and Multi-artifact Subspace Decomposition
Xiang Zhang, Wenliang Weng, Daoyong Fu +4
Deepfake detection remains highly challenging, particularly in cross-dataset scenarios and complex real-world settings. This challenge mainly arises because artifact patterns vary…
How Noise Benefits AI-generated Image Detection
Ziqiang Li, Jiazhen Yan, Fan Wang +2
The rapid advancement of generative models has made real and synthetic images increasingly indistinguishable. Although extensive efforts have been devoted to detecting AI-generated…
DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
Jiazhen Yan, Ziqiang Li, Fan Wang +3
The rapid progress of generative models such as GANs and diffusion models has led to the widespread proliferation of AI-generated images, raising concerns about misinformation, pri…
NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection
Jiazhen Yan, Fan Wang, Weiwei Jiang +3
The rapid progress of generative models, such as GANs and diffusion models, has facilitated the creation of highly realistic images, raising growing concerns over their misuse in s…
Is Artificial Intelligence Generated Image Detection a Solved Problem?
Ziqiang Li, Jiazhen Yan, Ziwen He +4
The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinfo…
A Comprehensive Survey on Visual Concept Mining in Text-to-image Diffusion Models
Ziqiang Li, Jun Li, Lizhi Xiong +2
Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals…
Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection
Jiazhen Yan, Ziqiang Li, Fan Wang +2
The rapid advancement of Generative Adversarial Networks (GANs) and diffusion models has enabled the creation of highly realistic synthetic images, presenting significant societal…