Safety of Multimodal Large Language Models on Images and Text
This paper systematically surveys current efforts on the evaluation, attack, and defense of MLLMs' safety on images and text.
Feb 1, 2024
MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
Analysis across 12 state-of-the-art models reveals that MLLMs are susceptible to breaches instigated by the approach, even when the equipped LLMs have been safety-aligned. Furthermore, this work proposes a straightforward yet effective prompting strategy to enhance the resilience of MLLMs against these types of attacks.
Nov 29, 2023
Improving zero-shot visual question answering via large language models with reasoning question prompts
Jan 1, 2023
Teach less, learn more: On the undistillable classes in knowledge distillation
Jan 1, 2022