all AI news
Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples
April 26, 2024, 4:45 a.m. | Kuofeng Gao, Jindong Gu, Yang Bai, Shu-Tao Xia, Philip Torr, Wei Liu, Zhifeng Li
cs.CV updates on arXiv.org arxiv.org
Abstract: Despite the exceptional performance of multi-modal large language models (MLLMs), their deployment requires substantial computational resources. Once malicious users induce high energy consumption and latency time (energy-latency cost), it will exhaust computational resources and harm availability of service. In this paper, we investigate this vulnerability for MLLMs, particularly image-based and video-based ones, and aim to induce high energy-latency cost during inference by crafting an imperceptible perturbation. We find that high energy-latency cost can be manipulated …
abstract arxiv availability computational consumption cost cs.ai cs.cv deployment energy harm language language models large language large language models latency manipulation mllms modal multi-modal paper performance resources samples service type via vulnerability will
More from arxiv.org / cs.CV 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