GPT in Sheep's Clothing: The Risk of Customized GPTs
arXiv:2401.09075v113 citationsh-index: 73
Originality Synthesis-oriented
AI Analysis
This addresses a security and privacy problem for users of AI services, but it is incremental as it builds on known risks in AI systems.
The paper tackles the problem of malicious use of customized GPTs introduced by OpenAI, highlighting that these models can pose privacy and security risks to users.
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.