Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity?
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910771240239104 |
|---|---|
| author | Fritz, Mario |
| author_facet | Fritz, Mario |
| contents | General Purpose AI - such as Large Language Models (LLMs) - have seen rapid deployment in a wide range of use cases. Most surprisingly, they have have made their way from plain language models, to chat-bots, all the way to an almost ``operating system''-like status that can control decisions and logic of an application. Tool-use, Microsoft co-pilot/office integration, and OpenAIs Altera are just a few examples of increased autonomy, data access, and execution capabilities. These methods come with a range of cybersecurity challenges. We highlight some of the work we have done in terms of evaluation as well as outline future opportunities and challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01435 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity? Fritz, Mario Cryptography and Security Artificial Intelligence General Purpose AI - such as Large Language Models (LLMs) - have seen rapid deployment in a wide range of use cases. Most surprisingly, they have have made their way from plain language models, to chat-bots, all the way to an almost ``operating system''-like status that can control decisions and logic of an application. Tool-use, Microsoft co-pilot/office integration, and OpenAIs Altera are just a few examples of increased autonomy, data access, and execution capabilities. These methods come with a range of cybersecurity challenges. We highlight some of the work we have done in terms of evaluation as well as outline future opportunities and challenges. |
| title | Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity? |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2501.01435 |