T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
Lijun Li, Zhelun Shi, Xuhao Hu, Bowen Dong, Yiran Qin, Xihui Liu, Lu Sheng, Jing Shao
2025Year
11Top-tier citations
Abstract
toxic content, and significant variation in privacy protection across the models, even with defense methods like concept erasing. Data and evaluator are released under https: //github.com/adwardlee/t2i_safety .
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers11
- RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for RoboticsEnshen Zhou, Jingkun An, Cheng Chi, Yi Han et al.NeurIPS 2025 · 159 citations
- Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context InjectionZiqi Miao, Yi Ding, Lijun Li, Jing ShaoEMNLP 2025 · 21 citations
- Response Attack: Exploiting Contextual Priming to Jailbreak Large Language ModelsZiqi Miao, Lijun Li, Yuan Xiong, Zhenhua Liu et al.AAAI 2026 · 8 citations
- Towards Policy-Adaptive Image Guardrail: Benchmark and MethodCaiyong Piao, Zhiyuan Yan, Haoming Xu, Yunzhen Zhao et al.CVPR 2026 · 7 citations
- Multimodal LLMs as Customized Reward Models for Text-to-Image GenerationShijie Zhou, Ruiyi Zhang, Huaisheng Zhu, Branislav Kveton et al.ICCV 2025 · 3 citations
Builds on26
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 7,873 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
Related papers
- Chinese Toxic Language Mitigation via Sentiment Polarity Consistent RewritesXintong Wang, Yixiao Liu, Jingheng Pan, Liang Ding et al.EMNLP 2025 · 1 citation
- SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video GenerationJaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao et al.ICLR 2025
- USD: NSFW Content Detection for Text-to-Image Models via Scene GraphYuyang Zhang, Kangjie Chen, Xudong Jiang, Jiahui Wen et al.USENIX Security 2025
- Successor Features for Efficient Multi-Subject Controlled Text GenerationMeng Cao, Mehdi Fatemi, Jackie C. K. Cheung, Samira ShabanianICML 2024 · 2 citations
- On the Challenges of Using Black-Box APIs for Toxicity Evaluation in ResearchLuiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara HookerEMNLP 2023 · 19 citations
