All Stories
January 2024
-
Prompt Injection Defence by Task-specific Fine-tuning
Jetmo from UC Berkeley generates task specific LLMs
December 2023
-
My WAF is reporting a URL Access Violation.
WAF meets MAP
-
AI Knows What You Typed
Researchers apply ML and AI to Side Channel Attacks
-
Local Inference Hardware
Truly private AI. Can it pay for itself?
-
Microsoft Training Data Exposure
Does your org manage its cloud storage tokens?
-
The Human Eval Gotcha
Always read the Eval label
-
LLM in 3D: Watch and marvel
3D browser render of LLM Visualization
-
llm gets plugins
My favourite command line llm tool grows wings
-
Freedom to Train AI
Clickworkers are part of the AI supply chain. How to vet?
-
Unembedding: reverse engineering PII from lists of numbers
Capture this in your threat model
Page 3 of 11