collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…