11 papers
Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation
Yuanmin Huang, Chen Chen, Geng Hong +5
Proprietary text-to-image diffusion models are increasingly distributed as hosted services and downloadable checkpoints, making their intellectual property (IP) protection an incre…
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…
It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents
Yiming Sun, Chen Chen, Zifan Zhou +1
Phone-use Agents can execute complex tasks end to end across real mobile applications. By operating a real device on the user's behalf, they reach far more functionalities than CLI…
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…
SEW: Strengthening Robustness of Black-box DNN Watermarking via Specificity Enhancement
Huming Qiu, Mi Zhang, Junjie Sun +3
To ensure the responsible distribution and use of open-source deep neural networks (DNNs), DNN watermarking has become a crucial technique to trace and verify unauthorized model re…