Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models

• URL: http://arxiv.org/abs/2510.03302v1
• Date: Tue, 30 Sep 2025 07:46:19 GMT
• Title: Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models
• Abstract summary: Concept erasure techniques have been widely deployed in T2I diffusion models to prevent inappropriate content generation for safety and copyright considerations.<n> established erasure methods exhibit degraded effectiveness, raising questions about their true mechanisms.<n>We propose textbfRevAm, a trajectory optimization framework that resurrects erased concepts by dynamically steering the denoising process.
• Score: 38.38751366738881
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Concept erasure techniques have been widely deployed in T2I diffusion models to prevent inappropriate content generation for safety and copyright considerations. However, as models evolve to next-generation architectures like Flux, established erasure methods (\textit{e.g.}, ESD, UCE, AC) exhibit degraded effectiveness, raising questions about their true mechanisms. Through systematic analysis, we reveal that concept erasure creates only an illusion of ``amnesia": rather than genuine forgetting, these methods bias sampling trajectories away from target concepts, making the erasure fundamentally reversible. This insight motivates the need to distinguish superficial safety from genuine concept removal. In this work, we propose \textbf{RevAm} (\underline{Rev}oking \underline{Am}nesia), an RL-based trajectory optimization framework that resurrects erased concepts by dynamically steering the denoising process without modifying model weights. By adapting Group Relative Policy Optimization (GRPO) to diffusion models, RevAm explores diverse recovery trajectories through trajectory-level rewards, overcoming local optima that limit existing methods. Extensive experiments demonstrate that RevAm achieves superior concept resurrection fidelity while reducing computational time by 10$\times$, exposing critical vulnerabilities in current safety mechanisms and underscoring the need for more robust erasure techniques beyond trajectory manipulation.

Related papers

• EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders [103.46709005379591]
  Concept erasure offers a principled remedy by removing unwanted semantics from pretrained models.<n>Existing approaches typically operate at a coarse quality, misaligned with the finegrained, distributed nature of concept representations.<n>We propose EraseSAE, a novel framework that leverages sparse autoencoders to achieve surgical concept erasure.
  arXiv  Detail & Related papers  (2026-09-03T10:23:37Z)
• Scaling Reinforcement Learning for Diffusion Models via Velocity Matching [66.34541945134916]
  RewardBench fine-tuning is an important tool for adapting diffusion models to human preferences and task-specific objectives.<n>Unlike autoregressive models, diffusion models do not provide tractable likelihoods for generated samples.<n>We propose reward-based velocity matching (RVM), a simple trajectory-free update that acts directly on the velocity field.
  arXiv  Detail & Related papers  (2026-08-24T17:13:43Z)
• FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models [47.80885954469943]
  Flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks.<n>We propose emphFlowErase-RL, the first GRPO-based framework for concept erasure in flow matching models.<n>We show that our method achieves state-of-the-art erasure performance while maintaining strong image quality and semantic alignment.
  arXiv  Detail & Related papers  (2026-05-19T12:10:09Z)
• Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework [10.018906972154218]
  Concept erasure aims to mitigate risks by removing specific concepts from pretrained models.<n>Recent studies show that such methods often suppress rather than fully eliminate target concepts, leaving models vulnerable to awakening attacks.<n>We propose ConceptAgent, a training-free, black-box, multi-agent framework that awakens erased concepts by initializing the denoising trajectory from surrogate-guided noisy states.
  arXiv  Detail & Related papers  (2026-05-18T09:55:36Z)
• Closed-Form Concept Erasure via Double Projections [8.357438653110973]
  Concept erasure is a process of removing unwanted concepts from generative models.<n>We present a linear transformation framework that achieves concept erasure analytically, without any training.<n>Our design yields a deterministic and geometrically interpretable procedure for safe, efficient, and theory-grounded concept removal.
  arXiv  Detail & Related papers  (2026-04-11T05:06:15Z)
• Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models [49.10620605347065]
  We propose Differential Vector Erasure (DVE), a training-free concept erasure method specifically designed for flow matching models.<n>Our key insight is that semantic concepts are implicitly encoded in the directional structure of the velocity field governing the generative flow.<n>During inference, DVE selectively removes concept-specific components by projecting the velocity field onto the differential direction, enabling precise concept suppression without affecting irrelevant semantics.
  arXiv  Detail & Related papers  (2026-02-01T08:05:45Z)
• ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models [12.021923446217722]
  Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models.<n>Existing adversarial approaches for exploiting this leakage are constrained by fundamental limitations.<n>We introduce ReLAPSe, a policy-based adversarial framework that reformulates concept restoration as a reinforcement learning problem.
  arXiv  Detail & Related papers  (2026-01-30T21:56:50Z)
• LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models [24.332916173317113]
  Concept erasure aims to suppress sensitive content in diffusion models.<n>Recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods.<n>We model the generation process as an implicit function to enable a comprehensive theoretical analysis of multiple factors.
  arXiv  Detail & Related papers  (2026-01-20T10:39:11Z)
• Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement [63.54516423266521]
  Pre-Trained Diffusion-Based (PTDB) methods often sacrifice content fidelity to attain higher perceptual realism.<n>We propose a novel optimization strategy for conditioning in pre-trained diffusion models, enhancing fidelity while preserving realism and aesthetics.<n>Our approach is plug-and-play, seamlessly integrating into existing diffusion networks to provide more effective control.
  arXiv  Detail & Related papers  (2025-10-20T02:40:06Z)
• Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack [37.88516477305766]
  We present ReFlux, the first concept attack method specifically designed to assess the robustness of concept erasure in the latest rectified flow-based T2I framework.<n>Our approach is motivated by the observation that existing concept erasure techniques, when applied to Flux, fundamentally rely on a phenomenon known as attention localization.
  arXiv  Detail & Related papers  (2025-10-01T08:12:07Z)
• Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving [55.13109926181247]
  We introduce ReflectDrive, a learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion.<n>Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient.<n>Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors.
  arXiv  Detail & Related papers  (2025-09-24T13:35:15Z)
• TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models [0.0]
  Concept erasure aims to remove or suppress specific concept information in a generative model.<n>Trajectory-Constrained Attentional Concept Erasure (TRACE) is a novel method to erase targeted concepts from diffusion models.<n>TRACE achieves state-of-the-art performance, outperforming recent methods such as ANT, EraseAnything, and MACE in terms of removal efficacy and output quality.
  arXiv  Detail & Related papers  (2025-05-29T10:15:22Z)
• Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion [56.35484513848296]
  This research introduces continual unlearning', a novel paradigm that enables the targeted removal of multiple specific concepts from foundational generative models.<n>We propose Decremental Unlearning without Generalization Erosion (DUGE) algorithm which selectively unlearns the generation of undesired concepts.
  arXiv  Detail & Related papers  (2025-03-17T23:17:16Z)
• Rethinking the Vulnerability of Concept Erasure and a New Method [9.044763606650646]
  Concept erasure (defense) methods have been developed to "unlearn" specific concepts through post-hoc finetuning.<n>Recent concept restoration (attack) methods have demonstrated that these supposedly erased concepts can be recovered using adversarially crafted prompts.<n>We introduce **RECORD**, a novel coordinate-descent-based restoration algorithm that consistently outperforms existing restoration methods by up to 17.8 times.
  arXiv  Detail & Related papers  (2025-02-24T17:26:01Z)
• Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models [76.39651111467832]
  We introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. To mitigate inappropriate content potentially represented by derived embeddings, RECE aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts.
  arXiv  Detail & Related papers  (2024-07-17T08:04:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.