OpenAI launches Lockdown Mode and Elevated Risk warnings to protect ChatGPT against prompt-injection attacks and reduce data-exfiltration risks.

CISA confirms active exploitation of CVE-2024-43468 in Microsoft Configuration Manager and urges immediate patching.

CISA ordered federal agencies on Thursday to secure their systems against a critical Microsoft Configuration Manager ...

This week, a CISA warning, Nest footage in Nancy Guthrie case, Signal phishing. Spanish hacker, Russian asylum. Spanish ...

In the threat-intel group's most recent AI Threat Tracker report, released on Thursday and shared with The Register in advance, Google attributes this activity to APT31, a Beijing-backed crew also ...

Google Threat Intelligence Group (GTIG) has published a new report warning about AI model extraction/distillation attacks, in ...

Oso reports on OpenClaw, an AI assistant that automates tasks but raises security concerns due to its access to sensitive data and external influences.

AI has steadily woven itself into every corner of security, its influence is only beginning to take shape. Identity is expanding beyond people, compliance is becoming part of everyday defense, and the ...

More than 40,000 WordPress sites using the Quiz and Survey Master plugin have been affected by a SQL injection vulnerability that allowed authenticated users to interfere with database queries. The ...

Local law enforcement, including these policemen walking past Piazza Duomo in Milan, handle most security functions at the Winter Games. A division of ICE is expected to aid Italian authorities' ...

A High-Risk SQL Injection vulnerability was discovered in the tagging system of the FOSSology web interface. The vulnerability allows an authenticated user to execute arbitrary SQL commands, leak ...

Prompt injections have become one of the biggest emerging threats to the modern home as AI adoption grows. It's a new era of malware -- and one that requires new defenses. Tyler Lacoma Editor / Home ...