4 papers
VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts
Peigui Qi, Kunsheng Tang, Yanpu Yu +7
Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer fr…
MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement
Xinyue Yu, Youqing Fang, Pingyu Wu +4
Generating expressive and controllable human speech is one of the core goals of generative artificial intelligence, but its progress has long been constrained by two fundamental ch…
Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models
Daiheng Gao, Nanxiang Jiang, Andi Zhang +5
Concept erasure techniques have been widely deployed in T2I diffusion models to prevent inappropriate content generation for safety and copyright considerations. However, as models…
Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation
Yufei Tang, Daiheng Gao, Pingyu Wu +3
In the realm of image generation, the quest for realism and customization has never been more pressing. While existing methods like concept sliders have made strides, they often fa…