all AI news
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
Feb. 22, 2024, 5:46 a.m. | Jiawei Liang, Siyuan Liang, Man Luo, Aishan Liu, Dongchen Han, Ee-Chien Chang, Xiaochun Cao
cs.CV updates on arXiv.org arxiv.org
Abstract: Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However, we uncover the potential threat posed by backdoor attacks on autoregressive VLMs during instruction tuning. Adversaries can implant a backdoor by injecting poisoned samples with triggers embedded in instructions or images, enabling malicious manipulation of the victim model's predictions with predefined triggers. Nevertheless, the frozen visual encoder in …
abstract arxiv attacks backdoor capabilities context cs.cv few-shot few-shot learning implant language language models multimodal threat type visual vlms
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Data Engineer
@ Quantexa | Sydney, New South Wales, Australia
Staff Analytics Engineer
@ Warner Bros. Discovery | NY New York 230 Park Avenue South