adversarial detection 1embedding space anisotropy 1geometric analysis 1multimodal robustness 1vision-language models 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings
Yubo Wang, Shujie Cui, James Bailey +5
Dense text embeddings are widely used in data mining, retrieval, and downstream machine learning systems due to their compact and semantically rich representations, but recent embe…
cs.CV2026
GeoDetect: Geometric Adversarial Detection for VLPs
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +2
The paper introduces GeoDetect, a method that uses geometric properties of vision‑language model embeddings to detect adversarial examples by measuring how far they deviate from th…