Dynamic Eraser for Guided Concept Erasure in Diffusion Models

• URL: http://arxiv.org/abs/2604.16483v1
• Date: Mon, 13 Apr 2026 02:25:14 GMT
• Title: Dynamic Eraser for Guided Concept Erasure in Diffusion Models
• Abstract summary: We present Dynamic Semantic Steering (DSS), a lightweight, training-free framework for interpretable and controllable concept erasure.<n> DSS achieves an average erasure rate of 91.0%, significantly outperforming SOTA methods (from 18.6% to 85.9%) with minimal impact on output fidelity.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while token-level interventions struggle with semantic granularity and context. Moreover, both types of methods are prone to severe semantic drift or even complete representation collapse. To address these challenges, we present Dynamic Semantic Steering (DSS), a lightweight, training-free framework for interpretable and controllable concept erasure. DSS introduces: 1) Sensitive Semantic Boundary Modeling (SSBM) to automate the discovery of safe semantic anchors, and 2) Sensitive Semantic Guidance (SSG), which leverages cross-attention features for precise detection and performs correction via a closed-form solution derived from a well-posed objective. This ensures optimal suppression of sensitive content while preserving benign semantics. DSS achieves an average erasure rate of 91.0\%, significantly outperforming SOTA methods (from 18.6\% to 85.9\%) with minimal impact on output fidelity.

Related papers

• GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models [16.95462517490593]
  GRACE is a structured concept erasure framework designed to enable localized and selective intervention.<n>We introduce a semantically weighted sensitive subspace estimation to precisely lock intervention directions.<n>We also introduce an energy-driven dynamic gating mechanism that adaptively controls the timing and strength of intervention at inference.
  arXiv  Detail & Related papers  (2026-09-11T11:29:37Z)
• UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation [90.0896070825457]
  We propose a unified noise-driven framework that rethinks safety mechanisms through the lens of noise dynamics in diffusion processes.<n>Our key insight is that early-stage predicted noise exhibits inherent separability between normal and sexually explicit content.<n>We develop a lightweight noise-based detector achieving superior accuracy with virtually no computational overhead.
  arXiv  Detail & Related papers  (2026-07-18T14:03:39Z)
• SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models [10.865745057624833]
  We introduce the first scale-aware concept erasure framework (SACE) for visual autoregressive ( VAR) models.<n>By strictly confining interventions to the first scale, our approach couples an Entropy-Regularized Erasure Objective to prevent high-entropy sampling degeneration.
  arXiv  Detail & Related papers  (2026-06-14T13:39:00Z)
• SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving [14.057807061501004]
  We introduce SECURE - Stable Early Collision Understanding Robust Embeddings, a framework that formally defines and enforces model robustness.<n>We propose a principled training methodology that fine-tunes a baseline model using a multi-objective loss, which minimizes divergence from a reference model and penalizes sensitivity to adversarial perturbations. Experiments on DAD and CCD datasets demonstrate that our approach not only significantly enhances robustness against various perturbations but also improves performance on clean data, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2026-04-01T19:42:32Z)
• SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models [67.84174763413178]
  We introduce SafeRedir, a lightweight inference-time framework for robust unlearning via prompt embedding redirection.<n>We show that SafeRedir achieves effective unlearning capability, high semantic and perceptual preservation, robust image quality, and enhanced resistance to adversarial attacks.
  arXiv  Detail & Related papers  (2026-01-13T15:01:38Z)
• Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models [27.672305802461377]
  We introduce a novel training-free, zero-shot framework for concept erasure that operates directly on text embeddings before the diffusion process.<n>We achieve superior completeness and robustness while preserving locality and image quality.<n>This robustness also allows our framework to function as a built-in threat detection system, offering a practical solution for safer text-to-image generation.
  arXiv  Detail & Related papers  (2025-10-26T22:04:17Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing [77.75609817898035]
  Large Language Models (LLMs) have demonstrated impressive performance across various tasks, yet they remain vulnerable to generating toxic content.<n>We propose textscAutoregressive textscReward textscGuided textscRe presentation textscEditing (ARGRE)<n>ARGRE explicitly models toxicity transitions within the latent representation space, enabling stable and precise reward-guided editing.
  arXiv  Detail & Related papers  (2025-09-24T03:40:32Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations [67.35596444651037]
  Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable.<n>We propose a Reliable Test-time Adaptation (ReTA) method that enhances reliability from two perspectives.
  arXiv  Detail & Related papers  (2025-07-13T05:37:33Z)
• Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization [22.225141381422873]
  There is a growing concern about text-to-image diffusion models creating harmful content.<n>Post-hoc model intervention techniques, such as concept unlearning and safety guidance, have been developed to mitigate these risks.<n>We propose the safe generation framework Detect-and-Guide (DAG) to perform self-diagnosis and fine-interpret self-regulation.<n>DAG achieves state-of-the-art safe generation performance, balancing harmfulness mitigation and text-following performance on real-world prompts.
  arXiv  Detail & Related papers  (2025-03-19T13:37:52Z)

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.