A recent breach involving Amazon’s AI coding assistant, Q, has raised fresh concerns about the security of large language model based tools. A hacker successfully added a potentially destructive ...

In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of ...

Do any of these bots use their own previous outputs as further training data? That's one way these exploits could spread beyond "the same user who asks the bot to do ...

This month OpenAI has taken a significant step forward by introducing the GPT Store, an online marketplace that boasts a vast array of specialized ChatGPT custom GPT AI models created by users. This ...