These 4 critical AI vulnerabilities are being exploited faster than defenders can respond ...

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

Google has disclosed that its Gemini artificial intelligence models are being increasingly exploited by state-sponsored hacking groups, signaling a major shift in how cyberattacks are planned and ...

Google’s Gemini AI is being used by state-backed hackers for phishing, malware development, and large-scale model extraction attempts.

ChatGPT writing a bypass for a web application firewall’s SQL injection filter Lucian Nițescu Nițescu also uses LLMs in his work, including custom prompts to ChatGPT or Ollama (locally-hosted GPT), ...

Zast.AI has raised $6 million in funding to secure code through AI agents that identify and validate software vulnerabilities ...

F5's Guardrails blocks prompts that attempt jailbreaks or injection attacks, and its AI Red Team automates vulnerability discovery in AI systems. Network and security teams managing enterprise ...

The best defense against prompt injection and other AI attacks is to do some basic engineering, test more, and not rely on AI to protect you. If you want to know what is actually happening in ...

Snowflake has thousands of enterprise customers who use the company's data and AI technologies. Though many issues with generative AI are solved, there is still lots of room for improvement. Two such ...

Microsoft's early embrace of advanced AI in its dev tooling continues apace with the new public preview of SQL database in Microsoft Fabric, the company's analytics/data platform. Fabric is a ...