AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Khanna, Danush, Kumar, Gurucharan Marthi Krishna, Ghosh, Basab, Narsupalli, Yaswanth, Jain, Vinija, Sharma, Vasu, Chadha, Aman, Das, Amitava
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.08885