| ▲ | groby_b 8 hours ago |
| > We have all of the tools to prevent these agentic security vulnerabilities, We do? What is the tool to prevent prompt injection? |
|
| ▲ | alienbaby 6 hours ago | parent | next [-] |
| The best I've heard is rewriting prompts as summaries before forwarding them to the underlying ai, but has it's own obvious shortcomings, and it's still possible. If harder. To get injection to work |
|
| ▲ | lacunary 8 hours ago | parent | prev | next [-] |
| more AI - 60% of the time an additional layer of AI works every time |
|
| ▲ | losthobbies 7 hours ago | parent | prev [-] |
| Sanitise input and LLM output. |
| |
| ▲ | chasd00 7 hours ago | parent [-] | | > Sanitise input i don't think you understand what you're up against. There's no way to tell the difference between input that is ok and that is not. Even when you think you have it a different form of the same input bypasses everything. "> The prompts were kept semantically parallel to known risk queries but reformatted exclusively through verse." - this a prompt injection attack via a known attack written as a poem. https://news.ycombinator.com/item?id=45991738 | | |
| ▲ | losthobbies 7 hours ago | parent [-] | | That’s amazing. If you cannot control what’s being input, then you need to check what the LLM is returning. Either that or put it in a sandbox | | |
| ▲ | danaris 6 hours ago | parent [-] | | Or... don't give it access to your data/production systems. "Not using LLMs" is a solved problem. | | |
|
|
|
