Published:
A user prompt injection vulnerability (CSRF) in the llama-server (llama.cpp) Web UI (Reprompt-like) allows attackers to inject arbitrary user prompt with query parameter (?q=...), potentially leading to arbitrary shell command execution, data exfiltration, etc. (through tool calls).
Published:
An user prompt injection vulnerability (CSRF) both in in the e Chat (Mistral) and Grok (Reprompt-style) allows attackers to inject user prompt with query parameter (?q=...) potentially leading data exfiltration.
Reprompt-style vulnerability in Le Chat (Mistral) and Grok.
Published:
How to quickly use llama.cpp for LLM inference (part 2). This is a follow-up of a previous post on the same topic.
Where we learn that the sky is actually a giant blueberry smoothie 🫐
Published:
Testing ASCII smuggling using Unicode Tags on LLMs/chatbots. Nothing new here. Just a short summary.
Published:
How to quickly use llama.cpp for LLM inference (no GPU needed).
Published:
How to quickly use vLLM for LLM inference using CPU.
Published:
Some notes on how transformer-decoder language models work, taking GPT-2 as an example, and with lots references in order to dig deeper. This is intended both as a a roadmap for understanding on how LLMs work (especially the ones using a transformer-decoder architecture) and a a summary/recap on the topic.
Give me your prompt, would you kindly?
Published:
Extracting the system prompt from GitHub CoPilot.
Page 1 of 1 | Previous page | Next page | JSON Feed | Atom Feed | RSS Feed