10 papers
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…