Malicious AI
February 19 2026Summary: An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and...
Read more
Summary: An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and...
Read more
The title of the post is”What AI Security Research Looks Like When It Works,” and I agree:
In the latest OpenSSL security release> on January 27, 2026, twelve...
Read more
Here are three papers describing different side-channel attacks against LLMs.
“Remote Timing Attacks on Efficient Language Model Inference“:
Abstract: Scaling up language models has significantly increased their capabilities. But larger...
Read more
Attacks against modern generative artificial intelligence (AI) large language...
Read moreThis is a current list of where and when I am scheduled to speak:
An exploration of the interesting question.
Read moreNew York is contemplating a bill that adds surveillance to 3D printers:
New York’s 20262027 executive budget bill (S.9005 / A.10005) includes language that should alarm every maker, educator,...
Read more
I just noticed that the ebook version of Rewiring Democracy is on sale for $5 on Amazon, Apple Books, Barnes & Noble, Books A Million, Google Play, Kobo, and...
Read moreInteresting research: “CHAI: Command Hijacking Against Embodied AI.”
Abstract: Embodied Artificial Intelligence (AI) promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense...
Read more
In 2023, the science fiction literary magazine Clarkesworld stopped accepting new submissions because so many were generated by artificial intelligence. Near as the editors could tell, many submitters...
Read more
Recent Comments