EMNLP Findings2025
Misalignment Attack on Text-to-Image Models via Text Embedding Optimization and Inversion
Zhijie Du, Daizong Liu, Pan Zhou
Abstract
Text embedding serves not only as a core component of modern NLP models but also plays a pivotal role in multimodal systems such as text-to-image (T2I) models, significantly facilitating user-friendly image generation through natural language instructions. However, while offering convenience, it also introduces additional risks. Misalignment issues in T2I models, whether caused by unintentional user inputs or targeted attacks, can negatively impact the reliability and ethics of these models. In this paper, we introduce TEOI, which fully considers the continuity and distribution characteristics of text embeddings. The framework directly optimizes the embeddings using gradient-based methods and then inverts them to obtain misaligned prompts of discrete tokens. The TEOI framework supports both text-modal and multimodal misalignment attacks, revealing the vulnerabilities of multimodal models that rely on text embeddings. Our work highlights the potential risks associated with embedding-based text representations in prevailing T2I models and provides a foundation for further research into robust and secure text-to-image generation systems.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- High-Resolution Image Synthesis with Latent Diffusion Models cites Zero-Shot Text-to-Image Generation
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites High-Resolution Image Synthesis with Latent Diffusion Models
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Zero-Shot Text-to-Image Generation
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Denoising Diffusion Probabilistic Models
Builds on41
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 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
- Zero-Shot Text-to-Image GenerationAditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray et al.ICML 2021 · 6,356 citations
Related papers
- On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign PromptsYixin Wu, Ning Yu, Michael Backes, Yun Shen et al.USENIX Security 2025
- PLA: Prompt Learning Attack Against Text-To-Image Generative ModelsXinqi Lyu, Yihao Liu, Yanjie Li, Bin XiaoICCV 2025 · 10 citations
- Are aligned neural networks adversarially aligned?Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski et al.NeurIPS 2023 · 412 citations
- Natural Language Induced Adversarial ImagesXiaopei Zhu, Peiyang Xu, Guanning Zeng, Yinpeng Dong et al.ACM MM 2024 · 1 citation
- Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data PoisoningShengfang Zhai, Yinpeng Dong, Qingni Shen, Shi Pu et al.ACM MM 2023 · 46 citations
