4 papers
A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
Zhixiao Wu, Yao Lu, Jie Wen +3
Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively impl…
Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis
Songping Wang, Yueming Lyu, Shiqi Liu +4
The rise of customized diffusion models has spurred a boom in personalized visual content creation, but also poses risks of malicious misuse, severely threatening personal privacy…
CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
Joshua Kazdan, Hao Sun, Jiaqi Han +2
Diffusion models have a tendency to exactly replicate their training data, especially when trained on small datasets. Most prior work has sought to mitigate this problem by imposin…
SpotActor: Training-Free Layout-Controlled Consistent Image Generation
Jiahao Wang, Caixia Yan, Weizhan Zhang +6
Text-to-image diffusion models significantly enhance the efficiency of artistic creation with high-fidelity image generation. However, in typical application scenarios like comic b…