3 papers
cs.CR2026
Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models
Kai Wang, Jiale Zhang, Chengcheng Zhu +2
Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus m…
cs.CR2025
Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models
Kang Wei, Xin Yuan, Fushuo Huo +5
Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to t…
cs.CR2024
EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection
Yuwen Qian, Shuchi Wu, Kang Wei +5
Federated self-supervised learning (FSSL) has recently emerged as a promising paradigm that enables the exploitation of clients' vast amounts of unlabeled data while preserving dat…