cs.CRNov 6, 2026

Beyond Prompt Attacks: Least-Action Auditing of Concept Erasure

Authors: Yifei Zhu

Organizations: Tohoku University

Abstract

Concept erasure, or concept unlearning, in text-to-image diffusion models is usually audited with prompt attacks. A prompt attack tests whether one conditioning string still retrieves the erased concept. It does not measure the probability that the frozen generator still assigns to that concept. We introduce least-action auditing of this residual probability, and evaluate it on Stable Diffusion concept-erasure checkpoints. The least-action barrier is the minimum control cost of driving the frozen reverse process into a detector-defined concept event. This cost equals the path-space KL divergence of conditioning the model on the event, and therefore the event's negative log-probability. The estimate ΔSrobΔS_{\mathrm{rob}} uses a CLIP∧\wedgeDINOv2 consensus terminal, with no retraining and no adversarial prompt. Across 1818 erased concept-mechanism pairs spanning object classes and NSFW nudity, ΔSrobΔS_{\mathrm{rob}} predicts deployment leakage counted on 1,5001{,}500 fresh samples per model by detectors excluded from the audit (pooled Spearman ρ=−0.76ρ{=}{-}0.76, p=5×10−4p{=}5{\times}10^{-4}). Within every audited concept, the eraser with the higher barrier leaks less (18/1818/18). On NSFW nudity the barrier orders the standard erasers exactly: UCE ΔSrob=3.9ΔS_{\mathrm{rob}}{=}3.9 (leak 16.4%16.4\%) << ESD 75.575.5 (9.8%9.8\%) << RECE 224.5224.5 (1.4%1.4\%), while Safe Latent Diffusion (SLD) stays near zero and leaks 85.5%85.5\% under explicit prompts. The same trajectories repair deployed checkpoints. An audit-guided closed-form patch reduces UCE nudity leakage from 16.2%16.2\% to 0/1,5000/1{,}500 and RECE church leakage by 3.3×3.3\times, where direction-count-matched random edits fail.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models

    Oct 4, 2026Kaiyuan Deng, Yuchen Li, Gen Li +5Diffusion Model UnlearningT2I Diffusion Models

  2. Certifying Concept Unlearning in Text-to-Image Diffusion Models

    Sep 10, 2026Mansi, Luca Marzari, Francesco LeofanteDiffusion Model UnlearningConcept Erasure

  3. TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models

    Aug 15, 2026Alireza Dehghanpour Farashah, Zhuan Shi, Negar Rostamzadeh +1Safe T2I GenerationAdversarial Robustness