Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

Researchers have discovered two vulnerabilities in the widely used Cursor AI-enabled integrated development environment (IDE) ...

Our goal was to make prompt security as simple as Stripe made payments: one API call, transparent pricing, no sales calls.” — Ian Ho, Founder, SafePrompt SAN ...

Researchers report a 76% success rate manipulating Apple Intelligence with prompt injection attacks. Apple reportedly ...

OpenAI has launched Lockdown Mode, an optional feature aimed at safeguarding users from prompt injection attacks, a growing threat targeting conversational AI systems.

MCP tool poisoning turns trusted AI agents into a control plane for data loss. Learn how threat actors manipulate tool ...

Opera browser has announced a new security feature called Paste Protect that aims to stop clipboard-based cyberattacks before ...

If you tend to copy/paste content from websites, you might be surprised to find yourself under the thrall of a ClickFix ...

As enterprises rapidly embrace multimodal AI capable of understanding both text and images, security researchers are discovering that these powerful new capabilities introduce equally sophisticated ...

AI memory transforms an AI system from a stateless tool into a learning collaborator. That unlocks powerful experiences, but ...

HiddenLayer, the leading AI security company, today announced a collaboration with Cohere, the world's leading sovereign AI ...