VESFlow edits the learned velocity field of flow matching models via a safe-conditional posterior to produce safe images in 4 sampling steps, with an optional risk filter and VESFlow+ variant that also repels from unsafe directions.
Ring-a-bell! how reliable are concept removal methods for diffusion models? ArXiv, abs/2310.10012
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 14verdicts
UNVERDICTED 14representative citing papers
SafeGen-Bench is a benchmark with 10 malicious categories that evaluates conditional T2V models on paired start frames and text prompts, finding unsafety scores up to 44.5 and 80% guardrail failure rate.
FlowErase-RL applies GRPO to reformulate concept erasure in flow matching models as reward optimization using a dynamic dual-path mechanism for target suppression and non-target preservation.
A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.
TrajShield is a training-free defense that reduces jailbreak success rates by 52.44% on average in text-to-video models by localizing and neutralizing risks through trajectory simulation and causal intervention.
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.
UVR is a training-free framework that uses attention modulation based on identified information flow stages in multimodal DiT attention to erase unsafe semantics in image synthesis and editing at 91% and 77% rates while preserving quality.
BEAP is a black-box embedding-aware prompting attack using LLM-guided search that raises attack success rate over 60% against unlearned diffusion models while keeping prompts undetectable.
TICoE achieves more precise and faithful concept erasure in text-to-image models by collaborating text and image data through a convex manifold and hierarchical learning, outperforming prior methods.
EGLOCE erases target concepts in diffusion models at inference time by optimizing latents with dual energy guidance that repels unwanted concepts while retaining prompt alignment.
SPOT projects prompts to a tau-safe set via total variation to cut inappropriate content 14-44% relative to baselines while preserving benign prompt behavior in frozen T2I models.
Defines CARE score and proposes ReCARE framework to preserve co-occurring benign concepts during targeted unlearning in diffusion models.
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
CoreUnlearn uses a Component Extraction Module and Swap Disentangling Strategy to remove only erasure-critical components from concept embeddings in diffusion models.
citing papers explorer
-
Safe Few-Step Generation via Velocity Editing
VESFlow edits the learned velocity field of flow matching models via a safe-conditional posterior to produce safe images in 4 sampling steps, with an optional risk filter and VESFlow+ variant that also repels from unsafe directions.
-
SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation
SafeGen-Bench is a benchmark with 10 malicious categories that evaluates conditional T2V models on paired start frames and text prompts, finding unsafety scores up to 44.5 and 80% guardrail failure rate.
-
FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
FlowErase-RL applies GRPO to reformulate concept erasure in flow matching models as reward optimization using a dynamic dual-path mechanism for target suppression and non-target preservation.
-
What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers
A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.
-
TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
TrajShield is a training-free defense that reduces jailbreak success rates by 52.44% on average in text-to-video models by localizing and neutralizing risks through trajectory simulation and causal intervention.
-
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.
-
Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows
UVR is a training-free framework that uses attention modulation based on identified information flow stages in multimodal DiT attention to erase unsafe semantics in image synthesis and editing at 91% and 77% rates while preserving quality.
-
Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
BEAP is a black-box embedding-aware prompting attack using LLM-guided search that raises attack success rate over 60% against unlearned diffusion models while keeping prompts undetectable.
-
Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
TICoE achieves more precise and faithful concept erasure in text-to-image models by collaborating text and image data through a convex manifold and hierarchical learning, outperforming prior methods.
-
EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure
EGLOCE erases target concepts in diffusion models at inference time by optimizing latents with dual energy guidance that repels unwanted concepts while retaining prompt alignment.
-
SPOT: Selective Prompt Projection via Total Variation for Inference-Only Safe Text-to-Image Generation
SPOT projects prompts to a tau-safe set via total variation to cut inappropriate content 14-44% relative to baselines while preserving benign prompt behavior in frozen T2I models.
-
Co-occurring associated retained concepts in Diffusion Unlearning
Defines CARE score and proposes ReCARE framework to preserve co-occurring benign concepts during targeted unlearning in diffusion models.
-
Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
-
CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models
CoreUnlearn uses a Component Extraction Module and Swap Disentangling Strategy to remove only erasure-critical components from concept embeddings in diffusion models.