GPT in Sheep's Clothing: The Risk of Customized GPTs
Sagiv Antebi, Noam Azulay, Edan Habler, Ben Ganon, Asaf Shabtai, Yuval, Elovici
TL;DR
This paper discusses the potential security and privacy risks associated with customized GPTs, highlighting the malicious uses enabled by user-specific modifications of ChatGPT.
Contribution
It introduces the concept of risks posed by personalized GPTs and emphasizes the need for awareness and mitigation strategies.
Findings
Customized GPTs can be exploited for malicious purposes
Privacy risks increase with user-specific modifications
Awareness of security issues is crucial for safe deployment
Abstract
In November 2023, OpenAI introduced a new service allowing users to create custom versions of ChatGPT (GPTs) by using specific instructions and knowledge to guide the model's behavior. We aim to raise awareness of the fact that GPTs can be used maliciously, posing privacy and security risks to their users.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Healthcare and Education · Privacy-Preserving Technologies in Data · Ethics and Social Impacts of AI
Methodstravel james