arXiv Machine Learning September 14, 2026 By Mansi, Luca Marzari, Francesco Leofante

Certifying Concept Unlearning in Text-to-Image Diffusion Models

Read the original on arXiv Machine Learning →

The paper introduces a certification framework for assessing concept unlearning in text-to-image diffusion models, offering high‑confidence guarantees with bounded error on residual concept leakage. Unlike prior methods that rely solely on attack success rates from automated prompt searches, this approach combines statistical certification with worst‑case analysis along concept‑relevant embedding directions to derive explicit upper bounds on leakage probability. Evaluations across NSFW content, artistic styles, and celebrity identities reveal that certified leakage bounds exceed standard attack success rates by 16.2%, highlighting significant residual risks overlooked by existing protocols.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computer Vision

2d ago

Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models

arXiv:2609.37537v1 Announce Type: new Abstract: Machine unlearning has emerged as a critical post-hoc safety measure to erase sensitive concepts from Text-to-Image (T2I) models without prohibitive re...

By Arian Komaei Koma, Seyed Amir Kasaei, Aida Aryafar, Matin Ghiasi, Ali Aghayari, Amirhossein Souri, Mohammad Mosayyebi, AmirMahdi Sadeghzadeh, Mohammad Hossein Rohban

diffusion benchmarks safety

arXiv AI

Sep 15

DSS: Dynamic Semantic Steering for Robust Concept Erasure in Diffusion Models

The paper introduces Dynamic Semantic Steering (DSS), a training‑free, inference‑time defense for robust concept erasure in text‑to‑image diffusion models. DSS models local semantic neighborhoods geometrically, automatically identifies benign semantic anchors, and applies context‑aware, constrained feature correction using cross‑attention signals. Experiments show DSS achieves an average erasure rate of 91.0%, outperforming prior defenses while reducing semantic drift and preserving generation fidelity.

By Qinghui Gong, Zhengchun Zhou, Hua Meng, Yihuai Liang, Yuxuan Zhang

diffusion robotics safety

arXiv AI

Jun 2

EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion

arXiv:2505. 13273v2 Announce Type: replace Abstract: Large text-to-image diffusion models rarely expose reliable signals of when a prompt is likely to produce a poorly aligned generation, especially when training data is undisclosed.

By Lucas Berry, Axel Brando, Wei-Di Chang, Juan Camilo Gamboa Higuera, David Meger

diffusion safety

arXiv Machine Learning

Aug 14

Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise

arXiv:2601. 21628v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy and copyright.

By Puwei Lian, Yujun Cai, Songze Li, Bingkun Bao

diffusion fine-tuning safety

arXiv Machine Learning

Jun 18

RUB: Evaluating Residual Knowledge in Unlearned Models

arXiv:2504. 14798v2 Announce Type: replace Abstract: Machine Unlearning (MUL) has emerged as a key mechanism for privacy protection and content regulation, yet current techniques often fail to guarantee the complete removal of sensitive information.

By Hao Xuan, Xingyu Li

diffusion benchmarks safety

Hugging Face Trending Papers

Jun 23

Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients

Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in healthcare, where patient medical images paired with clinical reports demand rigorous privacy safeguards.

fine-tuning multimodal benchmarks safety