Run Wang

7

Papers

45

Total Citations

Papers (7)

Perception-Guided Jailbreak Against Text-to-Image Models

Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection

Automated Red Teaming for Text-to-Image Models through Feedback-Guided Prompt Iteration with Vision-Language Models

TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution

Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation