#large language models
5 stories taggedlarge language models.
Who Is Keeping Your AI Assistant Honest
From hallucinations to data leaks, a new class of software is emerging to govern AI systems in production. Here is what the field looks like right now.
Over a Million Phishing Emails Used Hidden Text to Fool AI Security Filters
Researchers found that criminals are hiding innocent words inside malicious emails to confuse both traditional and AI-powered spam filters, and the technique is working.
A Botnet Author Asked an AI for Malware. The AI Left the Warning Label On.
Researchers found TuxBot v3 Evolution, a new IoT botnet whose creator appears to have copy-pasted AI-generated code, safety disclaimer and all.
CrowdStrike Flags Five New Ways Criminals Can Trick AI Into Obeying Them
Researchers have mapped out a fresh set of prompt injection attacks, where criminals feed deceptive instructions to AI systems to make them behave in harmful ways. Here is what each one does and why ordinary employees are part of the risk picture.
AI Assistants Are Inventing Fake Web Addresses — and Criminals Are Buying Them Up
Researchers at Palo Alto Networks found that AI tools routinely make up plausible-sounding website addresses that don't exist. Criminals are registering those addresses before anyone notices, and one already built a full fraud operation using the same AI trick.