The study investigates how the proportion of unsafe images in training data influences the safety of text‑to‑image models. By training identical models on corpora ranging from 0% to 9.6% unsafe content and evaluating 10,000 generations per model, the authors find that unsafe output increases monotonically with contamination, saturating at 26.4% for the highest contamination level. Filtering a fixed fraction of unsafe images is equally effective across different dataset sizes and does not degrade image quality, yet it cannot eliminate unsafe generation entirely, indicating that data curation and encoder choices are complementary but insufficient alone.
By Felix Friedrich, Lukas Helff, Niharika Hegde, Patrick Schramowski, Kristian Kersting
DiSCO is a zero‑shot, black‑box defense for text‑to‑image models that operates solely at the prompt level. It expands prompts with a distribution‑guided suffix using beam search and contrastive scoring against safe and unsafe image pools generated by the target model, iteratively refining until safe content is produced. The method improves safety on the I2P benchmark under various red‑teaming attacks, reducing attack success rates by 37.7% and 25.13% while preserving semantic fidelity and image coherence.
By Tong Zhang, Motasem Alfarra, Carlos Hinojosa, Christos Louizos, Bernard Ghanem
arXiv:2607. 22745v1 Announce Type: cross Abstract: Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation.
By Yi-Zhi Wang, Yichen Xiao, Linan Yue, Weibo Gao, Yichao Du, Pengfei Fang, Shimin Di, Min-Ling Zhang
The paper introduces COMIC, a reference‑aware safety gate designed for multimodal large language models (MLLMs). COMIC detects the operation requested by a user, identifies visual targets through OCR and open‑vocabulary proposals, and evaluates safety on explicit operation‑target pairs, using max‑risk aggregation and quality‑aware routing to decide whether to allow or block a request. Experiments on several open‑source MLLMs and jailbreak benchmarks show that COMIC improves robustness while maintaining benign utility and efficiency.
By Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie, Huayue Gu, Chenyu Wang, Honghui Xu
arXiv:2609.39688v1 Announce Type: cross
Abstract: Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment...
By Tobia Poppi, Silvia Cappelletti, Samuele Poppi, Marcella Cornia, Lorenzo Baraldi, Diego Garcia-Olano, Rita Cucchiara
arXiv:2606. 05290v1 Announce Type: cross Abstract: Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture.
By Tobia Poppi, Silvia Cappelletti, Sara Sarto, Florian Schiffers, Garin Kessler, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
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:2604. 05853v3 Announce Type: replace Abstract: Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse.
By Zonghao Ying, Haowen Dai, Lianyu Hu, Zonglei Jing, Quanchen Zou, Yaodong Yang, Aishan Liu, Xianglong Liu
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:2606. 27147v1 Announce Type: cross Abstract: Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens.
By Yunqi Xue, Zhijiang Li, Philip Torr, Jindong Gu
arXiv:2607. 00402v1 Announce Type: cross Abstract: Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts.
By Adeel Yousaf, Soumik Ghosh, James Beetham, Amrit Singh Bedi, Mubarak Shah
Decoupled Safety Control (DSC) is a plug‑in algorithm that improves training‑free safety guidance for diffusion models by separating the unsafe condition from the intervention process. Unlike existing coupled safety‑control chains, DSC determines the intervention based on the current generation state, reducing residual unsafe content and preserving benign‑generation quality. Experiments on standard safety benchmarks demonstrate that DSC achieves stronger unsafe‑content suppression while maintaining efficient inference.
By Huilin Zhou, Ruoxi Cheng, Yuhang Wang, Yuming Liu, Minghao Sun, Ruolong Ma, Lan Zhang