9 papers · 1 filter
AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models
Yuanmin Huang, Zhenfei Zhang, Mi Zhang +5
Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit…
FairFlow: Demystifying and Mitigating Stereotype Bias in Text-to-Image Diffusion Transformers
Chen Chen, Yuanmin Huang, Zhenfei Zhang +5
Multimodal diffusion transformers (MM-DiTs) have emerged as the prevalent backbone for modern text-to-image generation systems. However, they exhibit critical alignment vulnerabili…
Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows
Xiang Yang, Feifei Li, Mi Zhang +4
Diffusion transformers (DiTs) equipped with multimodal attention (MM-Attn) have become a dominant paradigm for image generation. However, preventing the generation of harmful conte…
Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations
Yuanmin Huang, Mi Zhang, Chen Chen +4
While diffusion models excel at generating high-quality images, their tendency to memorize training data poses significant privacy and copyright risks. In this work, we for the fir…
SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers
Xiang Yang, Feifei Li, Mi Zhang +3
Recent Text-to-Image (T2I) models based on rectified-flow transformers (e.g., SD3, FLUX) achieve high generative fidelity but remain vulnerable to unsafe semantics, especially when…
SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
Yiming Sun, Mi Zhang, Feifei Li +2
Despite Video Large Language Models having rapidly advanced in recent years, perceptual hallucinations pose a substantial safety risk, which severely restricts their real-world app…