ไม่สามารถเล่นวิดีโอนี้
ขออภัยในความไม่สะดวก
Using LLMs to build a defense against adversarial attacks
ฝัง
- เผยแพร่เมื่อ 4 ก.ค. 2024
- Evaluates LLMs when used as a defense against adversarial attacks.
Paper: arxiv.org/abs/...
Check out my upcoming live training to learn more about building with LLMs:
maven.com/dair...
#ai #machinelearning #science #datascience
Thanks for sharing
It is a good paper, but unfortunately use Llama guard, retrieval, rerank, etc. Will be LLMs slower in latency with a lot of inferences, those are the only disadvantages that I see.
Those are good points. I think they mention a few of these things in the discussion. Smaller language models may be more ideal here.