一作ACL 2026Findings· Findings of ACL
Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification
Xiangtao Meng · Yingkai Dong · Ning Yu · Li Wang · Zheng Li · Shanqing Guo
摘要
Text-to-image (T2I) generative models have achieved remarkable visual fidelity, yet remain vulnerable to generating unsafe content. Existing safety defenses typically intervene internally within the generative model, but suffer from severe concept entanglement, leading to degradation of benign ge...