# Detecting Malicious Concepts without Image Generation in AI-Generated Content (AIGC) Source: [Detecting Malicious Concepts without Image Generation in AI-Generated Content (AIGC)]() Collection index: [llms.txt]() Data updated: 2026-05-02T05:00:04.163Z Authors: Kun Xu, Wenying Wen, Shuren Qi, Tao Wang, Yushu Zhang, Yuming Fang Published: 2025-02-13T03:15:18.000Z ## Abstract The task of text-to-image generation has achieved tremendous success in practice, with emerging concept generation models capable of producing highly personalized and customized content. Fervor for concept generation is increasing rapidly among users, and platforms for concept sharing have sprung up. The concept owners may upload malicious concepts and disguise them with non-malicious text descriptions and example images to deceive users into downloading and generating malicious content. The platform needs a quick method to determine whether a concept is malicious to prevent the spread of malicious concepts. However, simply relying on concept image generation to judge whether a concept is malicious requires time and computational resources. Especially, as the number of concepts uploaded and downloaded on the platform continues to increase, this approach becomes impractical and poses a risk of generating malicious content. In this paper, we propose Concept QuickLook, the first systematic work to incorporate malicious concept detection into research, which performs detection based solely on concept files without generating any images. We define malicious concepts and design two operational modes for detection: concept matching and fuzzy detection. Extensive experiments demonstrate that the proposed Concept QuickLook can detect malicious concepts and demonstrate practicality in concept sharing platforms. We also design robustness experiments to further validate the effectiveness of the solution. We hope this work can initiate malicious concept detection tasks and provide some inspiration. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Concept Matching on Concept Matching Seen](): Concept Matching; Concept Matching Seen; Accuracy: 97.82. - [Concept Matching on Concept Matching Unseen](): Concept Matching; Concept Matching Unseen; Accuracy: 77.51. - [Fuzzy Detection on Malicious Concept Dataset Seen](): Fuzzy Detection; Malicious Concept Dataset Seen; Accuracy: 96.73. - [Fuzzy Detection on Malicious Concept Dataset (Unseen)](): Fuzzy Detection; Malicious Concept Dataset (Unseen); Accuracy: 70.51. ## Original sources and implementation [Original paper]() [PDF]()