DISARMframeworks/generated_pages/techniques/T0154.001.md

17 lines
1.2 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Technique T0154.001: AI LLM Platform
* **Summary**: OpenAIs ChatGPT, Googles Bard, Microsofts Turing-NLG, Googles T5 (Text-to-Text Transfer Transformer), and Facebooks BART are examples of AI LLM (Large Language Model) Platforms.<br><br>AI LLM Platforms are online platforms which allow people to create Accounts that they can use to interact with the platforms AI Large Language Model, to produce text-based content.<br><br>LLMs can create hyper-realistic synthetic text that is both scalable and persuasive. LLMs can largely automate content production, reducing the overhead in persona creation, and generate culturally appropriate outputs that are less prone to exhibiting conspicuous signs of inauthenticity.<br><br>Some platforms implement protections against misuse of AI by their users. Threat Actors have been observed bypassing these protections using prompt injections, poisoning, jailbreaking, or integrity attacks.
* **Belongs to tactic stage**: TA07
| Incident | Descriptions given for this incident |
| -------- | -------------------- |
| Counters | Response types |
| -------- | -------------- |
DO NOT EDIT ABOVE THIS LINE - PLEASE ADD NOTES BELOW