Fetching the paper…

Reading the bibliography…

Assessing Prompt Injection Risks in 200+ Custom GPTs · Around

2023

Assessing Prompt Injection Risks in 200+ Custom GPTs

Yu, Jiahao, Wu, Yuhang, Shu, Dong et al.

Original
PDF
Post on X

Understand

In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications.

The new feature - customization of ChatGPT models by users to cater to specific needs has opened new frontiers in AI utility.
However, this study reveals a significant security vulnerability inherent in these user-customized GPTs: prompt injection attacks.
Through comprehensive testing of over 200 user-designed GPT models via adversarial prompts, we demonstrate that these systems are susceptible to prompt injections.

Built on

Language models are unsupervised multitask learners
Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever · 2019
Earlier work this paper cites.
Introducing chatgpt
OpenAI · 2022
Earlier work this paper cites.

Similar

Ignore previous prompt: Attack techniques for language models
Original
Fábio Perez and Ian Ribeiro · 2022
Cited alongside, same era.
mportant for everyone publishing customgpts
Borriss · 2023
Cited alongside, same era.
Introducing gpts
OpenAI
Cited in the paper.
Gpt-4 technical report, 2023b
OpenAI
Cited in the paper.

Then

Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection
Original
Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, and Mario Fritz · 2023
Closest in time.
Prompt injection attack against llm-integrated applications
Original
Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, and Yang Liu · 2023
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…