Prompt injections, the malicious commands attackers embed into content to entice large language models to follow them, have been attackers’ go-to tool for turning AI platforms against their users. A well-phrased command sneaked into an email or calendar invitation is often all it takes to cause the LLM to exfiltrate sensitive data or follow other harmful actions.

Now, defenders are embracing the prompt injection, too.

A strong, sharp effect

Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down attacks from AI hacking agents. The prompts direct the attacking LLM to perform an action forbidden by its guardrails, the safety barriers AI developers erect to prevent it from taking harmful actions. The LLM responds by shutting down.

Read full article

Comments

© Getty Images

Alors que les trains sont appelés à jouer un rôle central dans la transition écologique, le réseau ferroviaire français est confronté au vieillissement de ses infrastructures et au changement climatique qui l’accentue. Tout comme ses voisins européens… À la différence que certains ont pris une...

Chemtrails are real enough. Government agencies have been spraying the atmosphere with aerosols for decades. Solar Radiation Modification techniques, particularly Stratospheric Aerosol Injection, are intended to combat global warming but the potential agricultural and ecological damage is very concerning. I relate these developments to biblical prophecies about apocalyptic events.