3 papers
cs.CV2025
AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
Yufan Liu, Wanqian Zhang, Huashan Chen +4
Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teami…
cs.CV2024
Prediction Exposes Your Face: Black-box Model Inversion via Prediction Alignment
Yufan Liu, Wanqian Zhang, Dayan Wu +3
Model inversion (MI) attack reconstructs the private training data of a target model given its output, posing a significant threat to deep learning models and data privacy. On one…
cs.CV2024
RealEra: Semantic-level Concept Erasure via Neighbor-Concept Mining
Yufan Liu, Jinyang An, Wanqian Zhang +5
The remarkable development of text-to-image generation models has raised notable security concerns, such as the infringement of portrait rights and the generation of inappropriate…