AIM Intelligence's red team breached Anthropic's Claude Opus 4.6 in just 30 minutes, exposing major security gaps as ...

A new study suggests that the advanced reasoning powering today’s AI models can weaken their safety systems.

Cisco tested eight major open-weight artificial intelligence models and found multi-turn jailbreak attacks succeeded nearly 93% of the time. (Image: Shutterstock) Enterprise artificial intelligence ...

Welcome to the age of AI hacking, in which the right prompts make amateurs into master hackers.

Today, I have a new favorite phrase: "Adversarial poetry." It's not, as my colleague Josh Wolens surmised, a new way to refer to rap battling. Instead, it's a method used in a recent study from a team ...

Threat actors are operationalizing AI to scale and sustain malicious activity, accelerating tradecraft and increasing risk for defenders, as illustrated by recent activity from North Korean groups ...

A smartphone displaying the logo of Claude, an AI language model developed by Anthropic. Correspondent Today’s newest AI models might be capable of helping would-be terrorists create bioweapons or ...

New protections inspect documents, metadata, prompts, and responses before AI models can be manipulated Indirect prompt ...

As new large language models, or LLMs, are rapidly developed and deployed, existing methods for evaluating their safety and discovering potential vulnerabilities quickly become outdated. To identify ...

Founded in 2024, Promptfoo began as an open-source framework for evaluating AI prompts and model behavior. It later expanded into a commercial platform used by developers and enterprise security teams ...

Zapier reports that AI security is crucial as AI usage grows, presenting risks like data breaches and adversarial attacks ...