@inproceedings{meng-etal-2026-beyond,
    title = "Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification",
    author = "Meng, Xiangtao  and
      Dong, Yingkai  and
      Yu, Ning  and
      Wang, Li  and
      Li, Zheng  and
      Guo, Shanqing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1394/",
    pages = "27986--27998",
    ISBN = "979-8-89176-395-1",
    abstract = "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 generation quality{---}a trade-off we term the Safety Tax. To overcome this limitation, we advocate a paradigm shift from destructive internal editing to external safety rectification. Following this principle, we propose SafePatch, a structurally isolated safety module that performs external, interpretable rectification without modifying the base model. The core backbone of SafePatch is architecturally instantiated as a trainable clone of the base model{'}s encoder, allowing it to inherit rich semantic priors and maintain representation consistency. To enable interpretable safety rectification, we construct a strictly aligned counterfactual safety dataset (ACS) for differential supervision training. Across nudity and multi-category bench- marks and recent adversarial prompt attacks, SafePatch achieves robust unsafe suppression (7{\%} unsafe on I2P) while preserving image quality and semantic alignment."
}