all InfoSec news
Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
May 1, 2024, 4:11 a.m. | Xuanli He, Jun Wang, Qiongkai Xu, Pasquale Minervini, Pontus Stenetorp, Benjamin I. P. Rubinstein, Trevor Cohn
cs.CR updates on arXiv.org arxiv.org
Abstract: The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that trigger malicious outputs. However, the impact of backdoor attacks on multilingual models remains under-explored. Our research focuses on cross-lingual backdoor attacks against multilingual LLMs, particularly investigating how poisoning the instruction-tuning data in one or two languages can affect the outputs in languages …
arxiv attacks backdoor backdoor attacks can conditions cs.cl cs.cr impact language language models large llms malicious training trigger troubles under
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Security Operations Manager-West Coast
@ The Walt Disney Company | USA - CA - 2500 Broadway Street
Vulnerability Analyst - Remote (WFH)
@ Cognitive Medical Systems | Phoenix, AZ, US | Oak Ridge, TN, US | Austin, TX, US | Oregon, US | Austin, TX, US
Senior Mainframe Security Administrator
@ Danske Bank | Copenhagen V, Denmark