# Position: Embodied AI Requires a Privacy-Utility Trade-off

arXiv: https://arxiv.org/abs/2605.05017 · HTML: https://mlsanity.com/paper/2605.05017/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 48 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 26 of 26)

- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory](https://mlsanity.com/paper/2310.17884/) (2023)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2304.03047/) (2023)
- [Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications](https://mlsanity.com/paper/2510.07077/) (2025)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [No Free Lunch Theorem for Security and Utility in Federated Learning](https://mlsanity.com/paper/2203.05816/) (2022)
- [Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning](https://mlsanity.com/paper/2508.10399/) (2025)
- [FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation](https://mlsanity.com/paper/2508.02190/) (2025)
- [Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation](https://mlsanity.com/paper/2504.15699/) (2025)
- [IndoorUAV: Benchmarking Vision-Language UAV Navigation in Continuous Indoor Environments](https://mlsanity.com/paper/2512.19024/) (2025)
- [Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2310.08565/) (2023)
- [FedVLN: Privacy-preserving Federated Vision-and-Language Navigation](https://mlsanity.com/paper/2203.14936/) (2022)
- [Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered](https://mlsanity.com/paper/2510.08464/) (2025)
- [adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems](https://mlsanity.com/paper/2303.04257/) (2023)
- [ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting](https://mlsanity.com/paper/2502.14780/) (2025)
- [Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models](https://mlsanity.com/paper/2509.23827/) (2025)
- [Privacy Risks in Reinforcement Learning for Household Robots](https://mlsanity.com/paper/2306.09273/) (2023)
- [Benchmarking LLM Privacy Recognition for Social Robot Decision Making](https://mlsanity.com/paper/2507.16124/) (2025)
- [DT-RaDaR: Digital Twin Assisted Robot Navigation using Differential Ray-Tracing](https://mlsanity.com/paper/2411.12284/) (2024)
- [Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning](https://mlsanity.com/paper/2211.14769/) (2022)
- [Robots as AI Double Agents: Privacy in Motion Planning](https://mlsanity.com/paper/2308.03385/) (2023)
- [Real-Time Privacy Preservation for Robot Visual Perception](https://mlsanity.com/paper/2505.05519/) (2025)
- [Privacy Risks of Robot Vision: A User Study on Image Modalities and Resolution](https://mlsanity.com/paper/2505.07766/) (2025)
- [Privacy-Utility-Bias Trade-offs for Privacy-Preserving Recommender Systems](https://mlsanity.com/paper/2511.22515/) (2025)

## Built on by (most cited first, 1 of 1)

- [Towards Trustworthy Physical Intelligence: From Theory to Practice Across Life Cycle](https://mlsanity.com/paper/2607.22877/) (2026)

## Abstract (arXiv)

Embodied AI (EAI) systems are rapidly transitioning from simulations into real-world domestic and other sensitive environments. However, recent EAI solutions have largely demonstrated advancements within isolated stages such as instruction, perception, planning and interaction, without considering their coupled privacy implications in high-frequency deployments where privacy leakage is often irreversible. This position paper argues that optimizing these components independently creates a systemic privacy crisis when deployed in sensitive settings, thereby advancing the position that privacy in EAI is a life cycle-level architectural constraint rather than a stage-local feature. To address these challenges, we propose Secure Privacy Integration in Next-generation Embodied AI (SPINE), a unified privacy-aware framework that treats privacy as a dynamic control signal governing cross-stage coupling throughout the entire EAI life cycle. SPINE decomposes the EAI pipeline into various stages and establishes a multi-criterion privacy classification matrix to orchestrate contextual sensitivity across stage boundaries. We conduct preliminary simulation and real-world case studies to conceptually validate how privacy constraints propagate downstream to reshape system behavior, illustrating the insufficiency of fragmented privacy patches and motivating future research directions into secure yet functional embodied AI systems. We detail the SPINE framework and case studies at https://github.com/rminshen03/EAI_Privacy_Position.