On the Robustness of Large Multimodal Models Against Image Adversarial Attacks

2023-12-06 · CVPR 2024 1 · Xuanming Cui, Alejandro Aparcedo, Young Kyun Jang, Ser-Nam Lim

Recent advances in instruction tuning have led to the development of State-of-the-Art Large Multimodal Models (LMMs). Given the novelty of these models, the impact of visual adversarial attacks on LMMs has not been thoroughly examined. We conduct a comprehensive study of the robustness of various LMMs against different adversarial attacks, evaluated across tasks including image classification, image captioning, and Visual Question Answer (VQA). We find that in general LMMs are not robust to visual adversarial inputs. However, our findings suggest that context provided to the model via prompts, such as questions in a QA pair helps to mitigate the effects of visual adversarial inputs. Notably, the LMMs evaluated demonstrated remarkable resilience to such attacks on the ScienceQA task with only an 8.10% drop in performance compared to their visual counterparts which dropped 99.73%. We also propose a new approach to real-world image classification which we term query decomposition. By incorporating existence queries into our input prompt we observe diminished attack effectiveness and improvements in image classification accuracy. This research highlights a previously under-explored facet of LMM robustness and sets the stage for future work aimed at strengthening the resilience of multimodal systems in adversarial environments.

📄 PDF Abstract BibTeX arXiv:2312.03777

Code (0)

등록된 구현이 없습니다.

Tasks

Image Captioning image-classification Image Classification Visual Question Answering (VQA)

Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

2024-04-30 · Wanqi Zhou, Shuanghao Bai, Danilo P. Mandic, Qibin Zhao 외

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primaril…

Adversarial Defense Adversarial Robustness Adversarial Text

How Robust is Google's Bard to Adversarial Image Attacks?

2023-09-21 · Yinpeng Dong, Huanran Chen, Jiawei Chen, Zhengwei Fang 외

Multimodal Large Language Models (MLLMs) that integrate text and other modalities (especially vision) have achieved unprecedented performance in various multimodal tasks. However, due to the unsolved adversarial robustne…

Adversarial Robustness Chatbot Face Detection

AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning

2024-07-30 · Maisha Binte Rashid, Pablo Rivas

Multimodal machine learning models that combine visual and textual data are increasingly being deployed in critical applications, raising significant safety and security concerns due to their vulnerability to adversarial…

Adversarial Robustness Computational Efficiency Decoder Image Captioning

Sparse vs Contiguous Adversarial Pixel Perturbations in Multimodal Models: An Empirical Analysis

2024-07-25 · Cristian-Alexandru Botocan, Raphael Meier, Ljiljana Dolamic

Assessing the robustness of multimodal models against adversarial examples is an important aspect for the safety of its users. We craft L0-norm perturbation attacks on the preprocessed input images. We launch them in a b…

CoDefend: Cross-Modal Collaborative Defense via Diffusion Purification and Prompt Optimization

2025-10-13 · Fengling Zhu, Boshi Liu, Jingyu Hua, Sheng Zhong arxiv

Multimodal Large Language Models (MLLMs) have achieved remarkable success in tasks such as image captioning, visual question answering, and cross-modal reasoning by integrating visual and textual modalities. However, the…

Visual Question Answering Image Captioning