<section class='slide'><div class='step-no'>Overview</div><h2>What you'll build</h2><p>Lessons 1 and 3 made retrieval <em>better</em>. This lesson makes it <em>safe ...

Classifier-based input filters (e.g. Anthropic's Constitutional Classifiers) are a front-line defense against prompt injection and jailbreaks. They are easy to make look great on paper and easy to ...

Zscaler found attackers using SEO poisoning and hidden prompts in malicious websites to manipulate AI agents into making cryptocurrency payments.

Florida’s accelerating use of the death penalty under Gov. DeSantis now includes rare same-day executions, echoing practices last seen decades ago.

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...

AI agent security now has a purpose-built open-source guardrail: Ant Group released SingGuard-NSFA, a free framework that catches prompt injection and credential-theft patterns before AI agents ...

SentinelOne says macOS.Gaslight uses prompt injection to mislead AI-based malware analysis, steal data, and use Telegram for ...

Attackers have begun embedding hidden instructions in websites to target AI agents, according to new research. Zscaler's ...

James Duckett, convicted of the 1987 rape and murder of an 11-year-old girl, has been scheduled for execution for the second ...

Discover how the Rogue Agent vulnerability in Google Dialogflow CX enabled persistent AI agent compromise, data exfiltration, ...