arXiv Machine Learning

Certifying Concept Unlearning in Text-to-Image Diffusion Models

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.

arXiv Computer Vision
Nov 9

What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers

The paper introduces a training‑free, inference‑time safeguard for Diffusion‑Transformer (DiT) text‑to‑image models that detects and suppresses risky content such as sexual, violent, or copyrighted imagery. By analyzing attention heads, the authors find that each head is sensitive to specific semantic concepts, enabling the creation of an Attention Head Vector (AHV) that serves as a discriminative signature for risky tokens. During generation, a momentum‑based strategy tracks token‑wise AHVs across denoising steps, and a sensitivity‑guided suppression mechanism dynamically reduces attention logits for identified risky tokens, effectively mitigating harmful outputs while maintaining visual quality and robustness against adversarial prompts.

By Chenyu Zhang, Lanjun Wang, Yueyang Cheng, Ruidong Chen, Wenhui Li, An-an Liu
arXiv Computer Vision
Sep 30

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
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
arXiv AI
Oct 15

No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models

The paper introduces AVCE, a method for verifiable concept erasure in diffusion models that audits latent representations to identify vulnerable directions and then edits cross‑attention and self‑attention projections in closed form. By fine‑tuning with pathway‑level auditing losses and orthogonal gradient projection, AVCE reduces attack success rates by 5.07× and improves auditing scores by 3.84× compared to the best baseline while maintaining generation quality.

By Kaiyuan Deng, Yuchen Li, Gen Li, Yang Xiao, Geng Yuan, Xiaoyong Yuan, Bo Hui, Xiaolong Ma
Hugging Face Trending Papers
Jun 19

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unseen domains while there is only one single domain available for training. One of the promising directions for achieving single-domain generalization is to generate out-of-domain (OOD) training data through data augmentation or image generation.

arXiv Computer Vision
Oct 7

The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models

The paper investigates how diffusion models, even after fine‑tuning to unlearn harmful concepts, still retain a linear residual of those concepts in token embeddings. It introduces SubAttack, a jailbreak method that extracts this residual by learning orthogonal attack tokens composed of interpretable textual elements, and SubDefense, a plug‑and‑play defense that projects out the same subspace to suppress the residual. Experiments show SubAttack outperforms prior attacks in power and transferability, while SubDefense offers stronger robustness and better preservation of safe generation quality.

By Siyi Chen, Yimeng Zhang, Sijia Liu, Qing Qu