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.
By Mansi, Luca Marzari, Francesco Leofante
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:2608. 03284v1 Announce Type: cross Abstract: Ensuring safety and policy compliance in text-to-image diffusion models remains a critical challenge, as benign or adversarial prompts can often elicit prohibited content, e.
By Jinya Sakurai, Shueicheng Yan, Xun Xu
NitroFusion2 introduces Text-Stream Adversarial Distillation (TSAD) and Aspect-Cued Discrimination (ACD) to use intermediate text-token states as adversarial representations in multimodal diffusion transformers. By conditioning the discriminator on aspects like typography, objects, or style, the method steers which properties are emphasized during training. The resulting model achieves comparable quality to conventional 4–8 step distillation in just 1–2 steps, producing sharp text and fine-grained details in one-step generation.
By Dar-Yen Chen, Yi-Zhe Song
Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.
arXiv:2412.07658v3 Announce Type: replace-cross
Abstract: Text-to-image diffusion models have rapidly transitioned from research prototypes to widely deployed tools. Along with their impressive capab...
By Anubhav Jain, Takashi Shibuya, Yuya Kobayashi, Yuhta Takida, Nasir Memon, Julian Togelius, Yuki Mitsufuji
arXiv:2502. 16167v2 Announce Type: replace-cross Abstract: Diffusion models (DMs) have advanced text-to-image (T2I) synthesis, yet their personalization capabilities raise serious privacy and copyright concerns.
By Xinwei Liu, Xiaojun Jia, Yuan Xun, Hua Zhang, Xiaochun Cao
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:2512. 08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age.
By Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis
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:2608.21869v1 Announce Type: cross
Abstract: Text-to-image (T2I) diffusion models offer powerful visual generation, but their controllability creates a critical safety challenge: adversarial pro...
By Shreyash Dhoot, Paras Dhiman, Arsh Abbas Naqvi, Aranbi Dutta, Aman Chadha, Vinija Jain, Amitava Das
arXiv:2603. 00133v2 Announce Type: replace-cross Abstract: Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement.
By Kairan Zhao, Eleni Triantafillou, Peter Triantafillou