AI Security

As cybersecurity experts make their way to the one-armed bandits and scorching heat in Las Vegas for Black Hat USA 2024 next week, the specter of the CrowdStrike Inc. debacle looms large ...

This blog is based on our conversation with Rob van der Veer, Senior Principal Expert at the Software Improvement Group. It explores the complex challenges of developing secure AI systems and the ...

OpenAI has a new Safety and Security Committee in place fewer than two weeks after disbanding its “superalignment” team, a year-old unit that was tasked with focusing on the long-term effects of ...

“All tested LLMs remain highly vulnerable to basic jailbreaks, and some will provide harmful outputs even without dedicated attempts to circumvent their safeguards,” the report noted ...

The custom policy wizard helps prevent data leaks in GenAI tools by using CDP, requires no coding, and offers adaptive, intuitive policies. “The real threat is in unstructured data, the kind of ...

North American software developers have reasonable confidence that generative AI can be a tool to improve the security of the software they're building. In other regions? Not so much ...

Moderately relevant AI made image about AI papers :-) steampunk ofc!Recently our team has written several papers and blogs focused on securing AI. What you will not see in these papers is anything ...

Gain insights on defending your AI apps from abuse based on our real-world experiences helping customers combat emerging adversarial threats ...

Gain insights on defending your AI apps from abuse based on our real-world experiences helping customers combat emerging adversarial threats ...

Protect AI has acquired Laiyer AI, a provider of open source software used to protect LLMs from security threats ...