all InfoSec news
LoRA-as-an-Attack! Piercing LLM Safety Under The Share-and-Play Scenario
March 4, 2024, 5:10 a.m. | Hongyi Liu, Zirui Liu, Ruixiang Tang, Jiayi Yuan, Shaochen Zhong, Yu-Neng Chuang, Li Li, Rui Chen, Xia Hu
cs.CR updates on arXiv.org arxiv.org
Abstract: Fine-tuning LLMs is crucial to enhancing their task-specific performance and ensuring model behaviors are aligned with human preferences. Among various fine-tuning methods, LoRA is popular for its efficiency and ease to use, allowing end-users to easily post and adopt lightweight LoRA modules on open-source platforms to tailor their model for different customization. However, such a handy share-and-play setting opens up new attack surfaces, that the attacker can render LoRA as an attacker, such as backdoor …
arxiv attack cs.ai cs.cl cs.cr efficiency end fine-tuning human llm llms lora modules performance platforms play popular safety scenario share task under
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
Premium Hub - CoE: Business Process Senior Consultant, SAP Security Role and Authorisations & GRC
@ SAP | Dublin 24, IE, D24WA02
Product Security Response Engineer
@ Intel | CRI - Belen, Heredia
Application Security Architect
@ Uni Systems | Brussels, Brussels, Belgium
Sr Product Security Engineer
@ ServiceNow | Hyderabad, India
Analyst, Cybersecurity & Technology (Initial Application Deadline May 20th, Final Deadline May 31st)
@ FiscalNote | United Kingdom (UK)