An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts
on Vision-Language Models

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models

14 March 2024

Jindong Gu

Philip H. S. Torr

Papers citing "An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models"

4 / 4 papers shown

Title
Image-based Multimodal Models as Intruders: Transferable Multimodal Attacks on Video-based MLLMs Linhao Huang Xue Jiang Zhiqiang Wang Wentao Mo Xi Xiao Bo Han Yongjie Yin Feng Zheng AAML 51 2 0 02 Jan 2025
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory Sensen Gao Xiaojun Jia Xuhong Ren Ivor Tsang Qing-Wu Guo AAML 38 14 0 19 Mar 2024
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models Junnan Li Dongxu Li Silvio Savarese Steven C. H. Hoi VLM MLLM 270 4,244 0 30 Jan 2023
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation Junnan Li Dongxu Li Caiming Xiong S. Hoi MLLM BDL VLM CLIP 392 4,137 0 28 Jan 2022