ML Security PapersNow You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation
Shristi Das Biswas, Arani Roy, Kaushik Roy · Purdue University
Defends T2I/T2V diffusion models against harmful content generation via instant training-free weight modification robust to red-teaming
Robust concept removal for text-to-image (T2I) and text-to-video (T2V) models is essential for their safe deployment. Existing methods, however, suffer from costly retraining, inference overhead, or vulnerability to adversarial attacks. Crucially, they rarely model the latent semantic overlap between the target erase concept and surrounding content -- causing collateral damage post-erasure -- and even fewer methods work reliably across both T2I and T2V domains. We introduce Instant Concept Erasure (ICE), a training-free, modality-agnostic, one-shot weight modification approach that achieves precise, persistent unlearning with zero overhead. ICE defines erase and preserve subspaces using anisotropic energy-weighted scaling, then explicitly regularises against their intersection using a unique, closed-form overlap projector. We pose a convex and Lipschitz-bounded Spectral Unlearning Objective, balancing erasure fidelity and intersection preservation, that admits a stable and unique analytical solution. This solution defines a dissociation operator that is translated to the model's text-conditioning layers, making the edit permanent and runtime-free. Across targeted removals of artistic styles, objects, identities, and explicit content, ICE efficiently achieves strong erasure with improved robustness to red-teaming, all while causing only minimal degradation of original generative abilities in both T2I and T2V models.