Home Videos RoboPAIR: jailbreaking LLM-Driven Robots

RoboPAIR: jailbreaking LLM-Driven Robots

8
0
🤖 check out more robots like this

In the past few months, we have seen plenty of robots that offer integration with large language models. While LLMs revolutionize robots with contextual reasoning and facilitate human-robot interaction, they open robots to risk of being jailbroken. RoboPAIR is an algorithm designed to jailbreak LLM-controlled robots. It “elicits harmful physical actions from LLM-controlled robots.” Here is what the researchers accomplished:

More like this ➡️ here

  • White-box setting: Full access to NVIDIA Dolphins self-driving LLM.
  • Gray-box setting: Partial access to Clearpath Robotics Jackal UGV with GPT-4o planner.
  • Black-box setting: Query access to GPT-3.5-integrated Unitree Robotics Go2.

According to the researchers, in many scenarios, they managed to achieve 100% attack success rate. In the above video, you can see how the robot was tricked to deliver an explosive package.

[HT]

*Our articles may contain aff links. As an Amazon Associate we earn from qualifying purchases. Please read our disclaimer on how we fund this site.