Record summary
A quick snapshot of what this page covers.
Risk profile
How this risk is described and categorized.
"EAI systems interact with huge amounts of data, creating significant privacy concerns. These systems are often trained on vast corpora and process a variety of data modalities— spanning visual, auditory, and tactile information—during deployment [12]. Like text-based virtual AI models, which are known to memorize and expose personally identifiable information [75, 76], commercial robots have been shown to disclose proprietary information through simple prompts [61]."
Suggested mitigations
Defenses that may help with related attacks.
Restrict Number of AI Model Queries
Control Access to AI Models and Data in Production
AI Telemetry Logging
Source
Research source for this risk, when available.
Included resource
Embodied AI: Emerging Risks and Opportunities for Policy Action
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.