Text-to-image diffusion models have revolutionized visual content generation, yet their deployment is hindered by a fundamental limitation: safety mechanisms enforce rigid, uniform standards that fail to reflect diverse user preferences shaped by age, culture, or personal beliefs. To address this, we propose Personalized Safety Alignment (PSA), a framework that transitions generative safety from static filtration to user-conditioned adaptation. We introduce Sage, a large-scale dataset capturing diverse safety boundaries across 1,000 simulated user profiles, covering complex risks often missed by traditional datasets. By integrating these profiles via a parameter-efficient cross-attention adapter, PSA dynamically modulates generation to align with individual sensitivities. Extensive experiments demonstrate that PSA achieves a calibrated safety-quality trade-off: under permissive profiles, it relaxes over-cautious constraints to enhance visual fidelity, while under restrictive profiles, it enforces state-of-the-art suppression, significantly outperforming static baselines. Furthermore, PSA exhibits superior instruction adherence compared to prompt-engineering methods, establishing personalization as a vital direction for creating adaptive, user-centered, and responsible generative AI. Our code, data, and models are publicly available at https://github.com/M-E-AGI-Lab/PSAlign.
IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis
School of Computer Science and Technology, Fudan University(复旦大学计算机科学与技术学院);Institute of Big Data, Fudan University(复旦大学大数据研究院);Purple Mountain Laboratories(紫金山实验室)
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
King Abdullah University of Science and Technology(国王阿卜杜勒·阿齐兹大学科学与技术学院);Provable Responsible AI and Data Analytics Lab(可证责任AI与数据分析实验室);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);China University of Petroleum-Beijing at Karamay(北京石油大学克拉玛依校区)
PTalker: Personalized Speech-Driven 3D Talking Head Animation via Style Disentanglement and Modality Alignment
College of Computer Science and Electronic Engineering(计算机科学与电子工程学院);Hunan University(湖南大学);School of Electronic Information(电子信息学院);Central South University(中南大学)
Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)