# Robustness, privacy and adversarial aspects

Area: [Diffusion models](https://mlsanity.com/diffusion/index.md). HTML: https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/

## Key facts

- Robustness, privacy and adversarial aspects: 928 papers on arXiv since 2020 (data through 14 Oct 2026).
- 216 of its 928 mapped papers (23%) cite “Erasing Concepts from Diffusion Models” (2023, arXiv 2303.07345).
- 208 of its 928 mapped papers (22%) cite “Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models” (2022, arXiv 2211.05105).
- 22 new papers 17 Sep–14 Oct.

## Most cited here

- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023), cited by 216 papers here
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022), cited by 208 papers here
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023), cited by 184 papers here
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023), cited by 149 papers here
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023), cited by 147 papers here
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023), cited by 137 papers here
- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024), cited by 135 papers here
- [Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?](https://mlsanity.com/paper/2310.10012/) (2023), cited by 131 papers here
- [To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now](https://mlsanity.com/paper/2310.11868/) (2023), cited by 116 papers here
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022), cited by 104 papers here

## New (17 Sep–14 Oct)

- [No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation](https://mlsanity.com/paper/2610.19717/) (2026-10-14)
- [Beyond User-Side Defenses: Image Protection in Open-Weight Diffusion Models](https://mlsanity.com/paper/2610.16835/) (2026-10-12)
- [Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning](https://mlsanity.com/paper/2610.14514/) (2026-10-10)
- [LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse](https://mlsanity.com/paper/2610.13333/) (2026-10-09)
- [WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models](https://mlsanity.com/paper/2610.12952/) (2026-10-09)
- [On the Intrinsic Limited Robustness of Latent-Based Watermarking](https://mlsanity.com/paper/2610.08178/) (2026-10-06)
- [Protective Perturbations Must Survive the Resize: Scale-Robust Image Immunization against Malicious Editing](https://mlsanity.com/paper/2610.07464/) (2026-10-05)
- [SPIN: Image Immunization Against Diffusion Editing via Single-Step Projection in Stochastic Neighborhoods](https://mlsanity.com/paper/2610.06334/) (2026-10-05)
- [Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models](https://mlsanity.com/paper/2610.05601/) (2026-10-04)
- [No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2610.05401/) (2026-10-04)
- [VisualErase: Dual-Branch Visual Trajectory Redirection for Robust Concept Erasure in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2610.05000/) (2026-10-04)
- [Protecting Sensitive Data in Image Synthesis via PAC-Private Adaptation for Diffusion Models](https://mlsanity.com/paper/2610.04038/) (2026-10-02)
- [DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation](https://mlsanity.com/paper/2610.02188/) (2026-10-01)
- [Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit Interference](https://mlsanity.com/paper/2610.01989/) (2026-10-01)
- [Debias Anything: Fairness with Diversity without Supervision in Diffusion Models](https://mlsanity.com/paper/2610.01815/) (2026-10-01)
- [Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models](https://mlsanity.com/paper/2609.39548/) (2026-09-30)
- [Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2609.37537/) (2026-09-29)
- [TANGO: Watermarking Masked Diffusion Language Models in Token Pairs](https://mlsanity.com/paper/2609.35224/) (2026-09-28)
- [You Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning](https://mlsanity.com/paper/2609.34137/) (2026-09-28)
- [Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure](https://mlsanity.com/paper/2609.33445/) (2026-09-27)
- [FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models](https://mlsanity.com/paper/2609.30980/) (2026-09-25)
- [LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models](https://mlsanity.com/paper/2609.25884/) (2026-09-22)