RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Words
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929431782621184 |
|---|---|
| author | Buscemi, Alessio Proverbio, Daniele |
| author_facet | Buscemi, Alessio Proverbio, Daniele |
| contents | The ethical implications and potentials for misuse of Generative Artificial Intelligence are increasingly worrying topics. This paper explores how easily the default ethical guardrails of ChatGPT, using its latest customization features, can be bypassed by simple prompts and fine-tuning, that can be effortlessly accessed by the broad public. This malevolently altered version of ChatGPT, nicknamed "RogueGPT", responded with worrying behaviours, beyond those triggered by jailbreak prompts. We conduct an empirical study of RogueGPT responses, assessing its flexibility in answering questions pertaining to what should be disallowed usage. Our findings raise significant concerns about the model's knowledge about topics like illegal drug production, torture methods and terrorism. The ease of driving ChatGPT astray, coupled with its global accessibility, highlights severe issues regarding the data quality used for training the foundational model and the implementation of ethical safeguards. We thus underline the responsibilities and dangers of user-driven modifications, and the broader effects that these may have on the design of safeguarding and ethical modules implemented by AI programmers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15009 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Words Buscemi, Alessio Proverbio, Daniele Computers and Society Artificial Intelligence Computation and Language The ethical implications and potentials for misuse of Generative Artificial Intelligence are increasingly worrying topics. This paper explores how easily the default ethical guardrails of ChatGPT, using its latest customization features, can be bypassed by simple prompts and fine-tuning, that can be effortlessly accessed by the broad public. This malevolently altered version of ChatGPT, nicknamed "RogueGPT", responded with worrying behaviours, beyond those triggered by jailbreak prompts. We conduct an empirical study of RogueGPT responses, assessing its flexibility in answering questions pertaining to what should be disallowed usage. Our findings raise significant concerns about the model's knowledge about topics like illegal drug production, torture methods and terrorism. The ease of driving ChatGPT astray, coupled with its global accessibility, highlights severe issues regarding the data quality used for training the foundational model and the implementation of ethical safeguards. We thus underline the responsibilities and dangers of user-driven modifications, and the broader effects that these may have on the design of safeguarding and ethical modules implemented by AI programmers. |
| title | RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Words |
| topic | Computers and Society Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2407.15009 |