all AI news
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
March 25, 2024, 4:45 a.m. | Jiawang Bai, Kuofeng Gao, Shaobo Min, Shu-Tao Xia, Zhifeng Li, Wei Liu
cs.CV updates on arXiv.org arxiv.org
Abstract: Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented backdoor. On downstream tasks, one victim model performs well on clean samples but predicts a specific target class whenever a specific trigger is present. For injecting a backdoor, existing attacks depend on a large amount of additional data to maliciously fine-tune the entire pre-trained CLIP …
abstract arxiv attacks backdoor clip cs.cv however image image recognition implanted language pre-training prompt prompt learning recognition samples tasks training type vision
More from arxiv.org / cs.CV updates on arXiv.org
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
1 day, 16 hours ago |
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
Intern Large Language Models Planning (f/m/x)
@ BMW Group | Munich, DE
Data Engineer Analytics
@ Meta | Menlo Park, CA | Remote, US