A striking study of LLM security issues:
- A striking study of LLM security issues:
- "We deployed 44 AI agents and offered the internet $170K to attack them.
- 1.8M attempts, 62K breaches, including data leakage and financial loss.
- 🚨 Concerningly, the same exploits transfer to live production agents… (example: exfiltrating emails through calendar event) 🧵"