Fetching the paper…

Reading the bibliography…

2024

Exfiltration of personal information from ChatGPT via prompt injection

Schwartzman, Gregory

Original
PDF
Post on X

Understand

We report that ChatGPT 4 and 4o are susceptible to a prompt injection attack that allows an attacker to exfiltrate users' personal data.

It is applicable without the use of any 3rd party tools and all users are currently affected.
This vulnerability is exacerbated by the recent introduction of ChatGPT's memory feature, which allows an attacker to command ChatGPT to monitor the user for the desired personal data.

Exfiltration of personal information from ChatGPT via prompt injection · Around

Built on

Evaluating the susceptibility of pre-trained language models via handcrafted adversarial examples
Original
Hezekiah J Branch, Jonathan Rodriguez Cefalu, Jeremy McHugh, Leyla Hujer, Aditya Bahl, Daniel del Castillo Iglesias, Ron Heichman, and Ramesh Darwishi · 2022
Earlier work this paper cites.
Ignore previous prompt: Attack techniques for language models
Original
Fábio Perez and Ian Ribeiro · 2022
Earlier work this paper cites.
Exploring prompt injection attacks
Jose Selvi · 2022
Earlier work this paper cites.
Chatgpt plugin exploit explained: From prompt injection to accessing private data
Embrace The Red · 2023
Earlier work this paper cites.

Similar

Openai begins tackling chatgpt data leak vulnerability
Embrace The Red · 2023
Cited alongside, same era.
Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection
Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, and Mario Fritz · 2023
Cited alongside, same era.
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
Cited alongside, same era.
Embrace the red
Embrace The Red
Cited in the paper.

Then

Owasp top 10 for llm applications
OWASP · 2023
Later among the works it cites.
Automatic tool invocation when browsing with chatgpt - threats and mitigations
Embrace The Red · 2024
Closest in time.
Chatgpt: Hacking memories with prompt injection
Embrace The Red · 2024
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…