Issue #79 Safety Edwin Dong, Lalit Julapalli
LLM Security (Prompt Injection, Adversarial Attacks), Simply Explained
Free editionPRO edition
This week’s PRO issue is accompanied by a Colab notebook with a thorough data poisoning example. We’ll compare how poisoned data affects a simple model and how to use noise to defend against it. As always, the code in this issue can be executed on a normal home PC and does not require a large amount of VRAM.
Large Language Models (LLMs) are now embedded in a wide range of services, from customer service chatbots to medical service transcription.
They are becoming increasingly useful and can perform many automated tasks on their own. However, LLMs are also a double-edged sword.
The field of LLM security aims to address vulnerabilities in LLM-based systems.
Without it, AI customer service representatives can provide unhelpful or malicious content, be generally untrustworthy, and even act in other unrelated roles.
This edition is for PRO members.
