Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hossen, Md Imran, Chilukoti, Sai Venkatesh, Shan, Liqun, Chen, Sheng, Cao, Yinzhi, Hei, Xiali
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2404.18567