Conditioned Activation Transport for T2I Safety Steering

Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inference-time intervention, we observe that linear activation steering frequently degrades image quality when applied to benign prompts. To address this trade-off, we first construct SafeSteerDataset, a contrastive dataset containing 2300 safe and unsafe prompt pairs with high cosine similarity. Leveraging this data, we propose Conditioned Activation Transport (CAT), a framework that employs a geometry-based conditioning mechanism and nonlinear transport maps. By conditioning transport maps to activate only within unsafe activation regions, we minimize interference with benign queries. We validate our approach on two state-of-the-art architectures: Z-Image and Infinity. Experiments demonstrate that CAT generalizes effectively across these backbones, significantly reducing Attack Success Rate while maintaining image fidelity compared to unsteered generations. Warning: This paper contains potentially offensive text and images.

Key Contributions

• SafeSteerDataset: a contrastive dataset of 2,300 semantically-aligned safe/unsafe prompt pairs across 23 subcategories, enabling precise isolation of toxic activation manifolds
• CAT (Conditioned Activation Transport): a nonlinear, geometry-conditioned activation steering framework that activates transport maps only within unsafe activation regions, minimizing interference on benign queries
• First comprehensive safety-steering validation across both Diffusion Transformer (Z-Image) and AutoRegressive (Infinity) T2I architectures

🛡️ Threat Analysis

Details

Similar Papers