TwoHamsters: Benchmarking Multi-Concept Compositional Unsafety in Text-to-Image Models

Computer Science > Cryptography and Security [Submitted on 17 Apr 2026] TwoHamsters: Benchmarking Multi-Concept Compositional Unsafety in Text-to-Image Models Chaoshuo Zhang, Yibo Liang, Mengke Tian, Chenhao Lin, Zhengyu Zhao, Le Yang, Chong Zhang, Yang Zhang, Chao Shen Despite the remarkable synthesis capabilities of text-to-image (T2I) models, safeguarding them against content violations remains a persistent challenge. Existing safety alignments primarily focus on explicit malicious concepts, often overlooking the subtle yet critical risks of compositional semantics. To address this oversight, we identify and formalize a novel vulnerability: Multi-Concept Compositional Unsafety (MCCU), where unsafe semantics stem from the implicit associations of individually benign concepts. Based on this formulation, we introduce TwoHamsters, a comprehensive benchmark comprising 17.5k prompts curated to probe MCCU vulnerabilities. Through a rigorous evaluation of 10 state-of-the-art models and 16 defense mechanisms, our analysis yields 8 pivotal insights. In particular, we demonstrate that current T2I models and defense mechanisms face severe MCCU risks: on TwoHamsters, FLUX achieves an MCCU generation success rate of 99.52%, while LLaVA-Guard only attains a recall of 41.06%, highlighting a critical limitation of the current paradigm for managing hazardous compositional generation. Subjects: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2604.15967 [cs.CR]   (or arXiv:2604.15967v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.15967 Focus to learn more Submission history From: Chaoshuo Zhang [view email] [v1] Fri, 17 Apr 2026 11:30:46 UTC (21,906 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)