Geometric Erasure by Contrastive Velocity Matching in Rectified Flows

• URL: http://arxiv.org/abs/2606.00140v1
• Date: Fri, 29 May 2026 00:02:41 GMT
• Title: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
• Abstract summary: We introduce GEM, a simple but highly effective erasure framework for Rectified Flow models.<n>We establish a principled bridge between trajectory-based unlearning grounded in Generative Flow Networks and classic teacher-guided erasure.
• Score: 16.74832704069658
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and copyright infringements. To address these challenges, concept erasure has emerged as a prospective safeguard. However, as the field gradually transitions from U-Net-based diffusion models to Rectified Flow Transformers, erasure research has struggled to keep pace. In this work, we introduce GEM, a simple but highly effective erasure framework for Rectified Flow models. As part of our contribution, we establish a principled bridge between trajectory-based unlearning grounded in Generative Flow Networks and classic teacher-guided erasure: we translate trajectory-based signals into a teacher-guided flow-matching setup that unifies the strengths of both paradigms. Concretely, a teacher provides complementary attraction and repulsion signals that we combine into a single geometric guidance objective, yielding targeted suppression of unwanted concepts while preserving benign generation.

Related papers

• FlowErase-OPD: Multi-Concept Erasure via Anchored On-Policy Distillation in Flow Matching Models [11.142782377709409]
  FlowErase-OPD is a framework for multi-concept erasure based on on-policy distillation (OPD)<n>Our approach first distills multiple single-concept erased models into a unified LoRA module and introduces Anchored Multi-Teacher Distillation (AMTD)<n>Experiments on nudity, object, and artistic-style erasure demonstrate that FlowErase-OPD consistently improves the trade-off between erasure effectiveness, image quality, and semantic alignment.
  arXiv  Detail & Related papers  (2026-08-07T08:58:13Z)
• 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)
• Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks [0.0]
  This paper formulates safety verification as a dynamic survival prediction and trajectory dynamics problem.<n>The Triple-tier Anomaly Defense (TRIAD) framework is proposed as a predictive model that maps multimodal and multi-turn conversational flow as a continuous trajectory.
  arXiv  Detail & Related papers  (2026-05-18T18:06:20Z)
• Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency [74.90075313101933]
  This paper revisits the same optical-flow primitive through a more local supervision design.<n>We use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop.<n>To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism.
  arXiv  Detail & Related papers  (2026-05-07T13:53:31Z)
• Rethinking Vector Field Learning for Generative Segmentation [50.08025820235397]
  Taming diffusion models for generative segmentation has attracted increasing attention.<n>We revisit diffusion segmentation from the perspective of vector field learning.<n>We propose a principled vector field reshaping strategy that augments the learned vanishing velocity field with a detached distance-aware correction term.<n>This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework.
  arXiv  Detail & Related papers  (2026-03-19T17:58:19Z)
• FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories [82.90132015584359]
  ReFlow has theoretical consistency with flow matching but suboptimal performance in practical scenarios.<n>We propose FlowSteer, a method unlocks the potential of ReFlow-based distillation by guiding the student along teacher's authentic generation trajectories.
  arXiv  Detail & Related papers  (2025-11-24T07:13:23Z)
• 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)
• Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models [38.38751366738881]
  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.
  arXiv  Detail & Related papers  (2025-09-30T07:46:19Z)
• Generative Model Inversion Through the Lens of the Manifold Hypothesis [98.37040155914595]
  Model inversion attacks (MIAs) aim to reconstruct class-representative samples from trained models.<n>Recent generative MIAs utilize generative adversarial networks to learn image priors that guide the inversion process.
  arXiv  Detail & Related papers  (2025-09-24T14:39:25Z)
• Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning [54.26807397329468]
  This work explores a previously overlooked vulnerability in distributed deep learning systems.<n>An adversary who intercepts the intermediate features transmitted between them can still pose a serious threat.<n>We propose an exploitation strategy specifically designed for distributed settings.
  arXiv  Detail & Related papers  (2025-07-09T20:09:00Z)
• Improving Black-Box Generative Attacks via Generator Semantic Consistency [51.470649503929344]
  generative attacks produce adversarial examples in a single forward pass at test time.<n>We enforce semantic consistency by aligning the early generator's intermediate features to an EMA teacher.<n>Our approach can be seamlessly integrated into existing generative attacks with consistent improvements in black-box transfer.
  arXiv  Detail & Related papers  (2025-06-23T02:35:09Z)

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.