all AI news
LoRA-as-an-Attack! Piercing LLM Safety Under The Share-and-Play Scenario
March 4, 2024, 5:47 a.m. | Hongyi Liu, Zirui Liu, Ruixiang Tang, Jiayi Yuan, Shaochen Zhong, Yu-Neng Chuang, Li Li, Rui Chen, Xia Hu
cs.CL 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 …
abstract arxiv cs.ai cs.cl cs.cr efficiency fine-tuning human llm llms lora modules performance platforms popular safety type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US