InfoSec News Nuggets 8/28/2025

One long sentence is all it takes to make LLMs misbehave Security researchers from Palo Alto Networks' Unit 42 have discovered the key to getting large language model (LLM) chatbots to ignore their guardrails, and it's quite simple. You just have to ensure that your prompt uses terrible grammar and is one massive run-on sentence like this one which includes all the information before any full stop which would give the guardrails a chance to…
Read More

InfoSec News Nuggets 9/12/2024

Utah social media law requiring age verification blocked by judge A federal judge halted a Utah child safety law requiring social platforms to verify the ages of their users. In an order on Tuesday, Judge Robert J. Shelby issued a preliminary injunction in favor of NetChoice, saying the law likely violates the First Amendment. NetChoice, the technology trade association that includes Meta, Snap, Google, and X, sued the state to block the law in December 2023, alleging it “violates the…
Read More

InfoSec News Nuggets 10/30/2023

Stanford University investigating cyberattack after ransomware claims  Stanford University is investigating a cybersecurity incident within its Department of Public Safety after a ransomware gang claimed it attacked the school on Friday. A spokesperson for the university directed Recorded Future News to a statement published late on Friday afternoon explaining that it is in the process of figuring out the details of the incident. “We are continuing to investigate a cybersecurity incident at the Stanford University…
Read More