8 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…
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…
ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
Yuquan Wang, Mi Zhang, Yining Wang +4
Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the m…
From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models
Wenxuan Li, Zhenfei Zhang, Mi Zhang +4
Large language models (LLMs) may memorize sensitive or copyrighted content, raising significant privacy and legal concerns. While machine unlearning has emerged as a potential reme…