R-ESC: Robustly Erasing Space Concepts via Stochastic Feature Remapping

Concept erasure and machine unlearning have emerged asa critical paradigm for enabling models to remove unwanted knowledgefrom learned representations at the level of classes, attributes, or higher-level semantics, motivated by the safety concerns surrounding moderngenerative AI models. However, existing approaches face three persis-tent challenges: (1) they often degrade utility on the remain concepts,(2) they often leave residual feature-level signals that enable recoveryof the forget concepts via x001Cne-tuning or representation probing, and (3)they impose substantial computational or memory overhead, limitingscalability. Prior work, such as Erasing Space Concept (ESC), moves to-ward structured removal in representation space, but achieving robusterasure with low overhead remains a challenge. To address this issue, wepropose Robustly Erasing Space Concepts (R-ESC), a framework for ro-bustly erasing space concepts via stochastic feature remapping. R-ESCintroduces three components: (i) prototype-orthogonal projection thatreduces interference by decorrelating forget and remain prototypes priorto erasure, (ii) stochastic multi-target remapping that blends forget pro-totypes into multiple remain prototypes to prevent re-separation andhinder recovery, and (iii) activation-mean prototypes that compress theerasure procedure to a single forward pass, yielding linear-time computa-tion with constant additional memory. Across extensive experiments, R-ESC maintains remain data utility, strengthens resistance to feature-levelrecovery, and scales to large models and datasets, providing a practicalpathway toward robust and ex001Ecient concept erasure.