Beyond Prompt Attacks: Least-Action Auditing of Concept Erasure
cs.CR, cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
- Diffusion Models Beat GANs on Image Synthesis
- Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustness
- Erasing Concepts from Diffusion Models
- Unified Concept Editing in Diffusion Models
- Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
- Denoising Diffusion Probabilistic Models
- BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion
- SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
- Erased or Dormant? Rethinking Concept Erasure Through Reversibility
- When Are Concepts Erased From Diffusion Models?
- DINOv2: Learning Robust Visual Features without Supervision
- Circumventing Concept Erasure Methods For Text-to-Image Generative Models
- Diffusion Density Estimators
- On the Separability of Information in Diffusion Models
- Learning Transferable Visual Models From Natural Language Supervision
- Rethinking the Vulnerability of Concept Erasure and a New Method
- High-Resolution Image Synthesis with Latent Diffusion Models
- Side Effects of Erasing Concepts from Diffusion Models
- Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data