Trusted AI Blog

• LLM Security

Today let us focus on the top security concerns surrounding Large Language Models.

Japanese police have arrested a 25-year-old man from Kawasaki for allegedly using generative AI tools to create computer viruses.

This week in AI security: the European Union passed the world's first comprehensive law regulating artificial intelligence.

OpenAI has disbanded its team focused on the long-term risks of artificial intelligence, a person familiar with the situation confirmed to CNBC.

This week in AI security: Elastic Security Labs guidance on LLM risks and abuses, three new Cloud Security Alliance papers, and an AI governance link hub.

• LLM Security

The digest aims to raise awareness and provide valuable resources for those who are navigating the complex landscape of LLM Security.

This week in AI security: NIST released four guides exploring the risks set out in its 2023 AI Risk Management Framework.

LLMs present a vulnerability: prompt injections, a substantial security flaw for which there seems to be no straightforward solution.

The National Security Agency (NSA) has unveiled a comprehensive set of recommendations aimed at bolstering the security of AI systems.

• GenAI Security

This week in AI security: a new book on generative AI security theory and practice, an executive panel on GenAI risk and reward, and AI's darker side.

• LLM Security

Welcome to our LLM Security TOP Digest! Discover the latest news in LLM security with our selection of top articles and research findings.

This week in AI security: Grok explaining how to hot-wire a car, the Zscaler ThreatLabz 2024 AI Security Report, and a test of what chatbots refuse to say.