作者位次 #2/3ACL 2026Poster· Natural Language Processing
One Single Hub Text Breaks CLIP : Identifying Vulnerabilities in Cross-Modal Encoders via Hubness
Hiroyuki Deguchi · Katsuki Chousa · Yusuke Sakai
摘要
The hubness problem, in which hub embeddings are close to many unrelated examples, occurs often in high-dimensional embedding spaces and may pose a practical threat for purposes such as information retrieval and automatic evaluation metrics.In particular, since cross-modal similarity between text...