Indirect Prompt Injection Attacks Against LLM Assistants
September 3 2025Really good research on practical attacks against LLM agents.
Abstract: The growing integration...
Read more
Really good research on practical attacks against LLM agents.
Abstract: The growing integration...
Read more
In the early 1960s, National Security Agency cryptanalyst and cryptanalysis instructor Lambros D. Callimahos coined the term “Stethoscope” to describe a diagnostic computer program used to unravel the internal...
Read moreFirst-person account of someone accidentally catching several Humboldt squid on a fishing line. No photos, though. As usual, you can also use this squid post to talk about the security...
Read moreI just heard about this:
There’s a travel scam warning going around the internet right now: You should keep your baggage tags on your bags until you get...
Read more
The US Director of National Intelligence is reporting that the UK government is dropping its backdoor mandate against the Apple iPhone. For now, at least, assuming that Tulsi Gabbard...
Read moreNice indirect prompt injection attack:
Bargury’s attack starts with a poisoned document, which is shared to a potential victim’s Google Drive. (Bargury says a victim could have also...
Read more
I wrote about this in 2023. Here’s the story:
Three Dutch security analysts discovered the vulnerabilities—five in total—in a European radio standard called TETRA (Terrestrial Trunked Radio), which...
Read more
Look at this: McDonald’s chose the password “123456” for a major corporate system.
Read moreNice short article on the bobtail squid. As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered. Blog moderation...
Read moreThis academic year, I am taking a sabbatical from the Kennedy School and Harvard University. (It’s not a real sabbatical—I’m just an adjunct—but it’s the same idea.) I will...
Read more
Recent Comments