Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security

C. Dwork, “Differential privacy,” in

2006

Earlier work this paper cites.

Y. Nesterov and V. Spokoiny, “Random gradient-free minimization of convex functions,”

2017

Earlier work this paper cites.

S. Li, M. Xue, B. Z. H. Zhao, H. Zhu, and X. Zhang, “Invisible backdoor attacks on deep neural networks via steganography and regularization,”

2021

Earlier work this paper cites.

S. Li, H. Liu, T. Dong, B. Z. H. Zhao, M. Xue, H. Zhu, and J. Lu, “Hidden backdoors in human-centric language models,” in

2021

Earlier work this paper cites.

X. Yin, Y. Zhu, and J. Hu, “A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions,”

2021

Earlier work this paper cites.

R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High-resolution image synthesis with latent diffusion models,” in

2022

Earlier work this paper cites.

J. Zhang, Q. Yi, and J. Sang, “Towards adversarial attack on vision-language pre-training models,” in

2022

Earlier work this paper cites.

J. Ji, T. Qiu, B. Chen, B. Zhang, H. Lou, K. Wang, Y. Duan, Z. He, J. Zhou, Z. Zhang,

Original

2023

Earlier work this paper cites.

J. Fan, M. Xu, Z. Liu, H. Ye, C. Gu, D. Niyato, and K.-Y. Lam, “A learning-based incentive mechanism for mobile aigc service in decentralized internet of vehicles,” in

2023

Earlier work this paper cites.

E. Shayegani, Y. Dong, and N. Abu-Ghazaleh, “Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models,” in

2023

Earlier work this paper cites.

Y. Gong, D. Ran, J. Liu, C. Wang, T. Cong, A. Wang, S. Duan, and X. Wang, “Figstep: Jailbreaking large vision-language models via typographic visual prompts,”

Original

2023

Earlier work this paper cites.

E. Shayegani, M. Mamun, Y. Fu, P. Zaree, Y. Dong, and N. Abu-Ghazaleh, “Survey of vulnerabilities in large language models revealed by adversarial attacks. arxiv. doi: 10.48550,”

2023

Earlier work this paper cites.

X. Huang, W. Ruan, W. Huang, G. Jin, Y. Dong, C. Wu, S. Bensalem, R. Mu, Y. Qi, X. Zhao,

Original

2023

Earlier work this paper cites.

C. Schlarmann and M. Hein, “On the adversarial robustness of multi-modal foundation models,” in

2023

Earlier work this paper cites.

X. Qi, K. Huang, A. Panda, M. Wang, and P. Mittal, “Visual adversarial examples jailbreak aligned large language models,” in

2023

Earlier work this paper cites.

L. Bailey, E. Ong, S. Russell, and S. Emmons, “Image hijacks: Adversarial images can control generative models at runtime,”

Original

2023

Earlier work this paper cites.

E. Bagdasaryan, T.-Y. Hsieh, B. Nassi, and V. Shmatikov, “(ab) using images and sounds for indirect instruction injection in multi-modal llms,”

Original

2023

Earlier work this paper cites.

Y. Wu, X. Li, Y. Liu, P. Zhou, and L. Sun, “Jailbreaking gpt-4v via self-adversarial attacks with system prompts,”

Original

2023

Earlier work this paper cites.

Y. Dong, H. Chen, J. Chen, Z. Fang, X. Yang, Y. Zhang, Y. Tian, H. Su, and J. Zhu, “How robust is google’s bard to adversarial image attacks?,”

Original

2023

Earlier work this paper cites.

X. Wang, Z. Ji, P. Ma, Z. Li, and S. Wang, “Instructta: Instruction-tuned targeted attack for large vision-language models,”

Original

2023

Earlier work this paper cites.

E. Bagdasaryan and V. Shmatikov, “Ceci n’est pas une pomme: Adversarial illusions in multi-modal embeddings,”

Original

2023

Earlier work this paper cites.

D. Han, X. Jia, Y. Bai, J. Gu, Y. Liu, and X. Cao, “Ot-attack: Enhancing adversarial transferability of vision-language models via optimal transport optimization,”

Original

2023

Earlier work this paper cites.

J. Rehberger, “Image to prompt injection with google bard.”

2023

Earlier work this paper cites.

D. Lu, Z. Wang, T. Wang, W. Guan, H. Gao, and F. Zheng, “Set-level guidance attack: Boosting adversarial transferability of vision-language pre-training models,” in

2023

Earlier work this paper cites.

Z. Zhou, S. Hu, M. Li, H. Zhang, Y. Zhang, and H. Jin, “Advclip: Downstream-agnostic adversarial examples in multimodal contrastive learning,” in

2023

Cited alongside, same era.

Z. Yin, M. Ye, T. Zhang, T. Du, J. Zhu, H. Liu, J. Chen, T. Wang, and F. Ma, “Vlattack: Multimodal adversarial attacks on vision-language tasks via pre-trained models,”

Original

2023

Cited alongside, same era.

Y. Wang, W. Hu, Y. Dong, and R. Hong, “Exploring transferability of multimodal adversarial samples for vision-language pre-training models with contrastive learning,”

Original

2023

Cited alongside, same era.

B. He, X. Jia, S. Liang, T. Lou, Y. Liu, and X. Cao, “Sa-attack: Improving adversarial transferability of vision-language pre-training models via self-augmentation,”

Original

2023

Cited alongside, same era.

P. Chao, A. Robey, E. Dobriban, H. Hassani, G. J. Pappas, and E. Wong, “Jailbreaking black box large language models in twenty queries,”

Z. Tan, C. Zhao, R. Moraffah, Y. Li, Y. Kong, T. Chen, and H. Liu, “The wolf within: Covert injection of malice into mllm societies via an mllm operative,”

Original

2024

Closest in time.

M. Qraitem, N. Tasnim, K. Saenko, and B. A. Plummer, “Vision-llms can fool themselves with self-generated typographic attacks,”

Original

2024

Closest in time.

Z. Niu, H. Ren, X. Gao, G. Hua, and R. Jin, “Jailbreaking attack against multimodal large language model,”

Original

2024

Closest in time.

X. Tao, S. Zhong, L. Li, Q. Liu, and L. Kong, “Imgtrojan: Jailbreaking vision-language models with one image,”

Original

2024

Closest in time.

Y. Xu, J. Yao, M. Shu, Y. Sun, Z. Wu, N. Yu, T. Goldstein, and F. Huang, “Shadowcast: Stealthy data poisoning attacks against vision-language models,”