Skip to content
AI News HubLIVE
Original source2 min read

Seeing Less Is Not Seeing Safely: Privacy Leakage from Task-Scoped Robot Perception Exports

Summary

A new arXiv paper shows that domestic robots can leak private household information through exported structured representations even when raw sensor data stays local. The authors propose Task-Functional Perception Distillation (TFPD), evaluating navigation, collision checking, and object-goal execution across 120 AI2-THOR scenes. They find that task-equivalent exports can have vastly different privacy risks, and no universal privacy ordering exists from field removal or stronger abstraction.

SourcearXiv RoboticsAuthor: Yuqiao Xu, Erman Ayday
Seeing Less Is Not Seeing Safely: Privacy Leakage from Task-Scoped Robot Perception Exports
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 2 Sep 2026]

Title:Seeing Less Is Not Seeing Safely: Privacy Leakage from Task-Scoped Robot Perception Exports

View a PDF of the paper titled Seeing Less Is Not Seeing Safely: Privacy Leakage from Task-Scoped Robot Perception Exports, by Yuqiao Xu and 1 other authors

View PDF HTML (experimental)

Abstract:Domestic robots rely on rich perception to operate in private homes, but privacy risk persists even when raw sensor data remain local. Structured representations exported to downstream planners, cloud services, logs, or learning pipelines can still reveal household information through semantics, geometry, spatial structure, and task targets. We introduce Task-Functional Perception Distillation (TFPD), a task-scoped representation-export framework that keeps rich perception local and profiles downstream exports according to task utility, direct exposure, and multiple residual inference risks. Using 120 AI2-THOR scenes with scene-disjoint train/validation/test splits, frozen attacker selection, and representation-aware held-out attacks, we evaluate navigation, collision checking, and object-goal execution. Three navigation exports achieve identical success (1.000) and mean path ratio (0.898), yet representation-level linkability ranges from 0.532 to 0.970. Replacing an explicit target label with a target region reduces target-category macro-F1 from 1.000 to 0.077 while preserving success at 0.995, while geometric coarsening reduces object-category macro-F1 from 0.704 to 0.556 at a measurable collision-utility cost. A ProcTHOR replication preserves the navigation task-equivalence/privacy-inequivalence finding while changing the relative ordering of normalized and topological exports. These results show that neither field removal nor stronger abstraction induces a universal privacy ordering and motivate task-specific, multi-risk evaluation of the complete public representation.

Subjects:

Robotics (cs.RO); Cryptography and Security (cs.CR)

Cite as: arXiv:2609.03055 [cs.RO]

(or arXiv:2609.03055v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.03055

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yuqiao Xu [view email] [v1] Wed, 2 Sep 2026 18:29:08 UTC (4,113 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Seeing Less Is Not Seeing Safely: Privacy Leakage from Task-Scoped Robot Perception Exports, by Yuqiao Xu and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-09

Change to browse by:

cs cs.CR

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • TFPD is a task-scoped representation-export framework that keeps rich perception local and profiles exports for utility and residual inference risks.
  • Three navigation exports matched performance (success 1.000, path ratio 0.898) yet linkability ranged from 0.532 to 0.970.
  • Target-region substitution slashed target-category macro-F1 from 1.000 to 0.077 while preserving success at 0.995.
  • A ProcTHOR replication preserved task-equivalence/privacy-inequivalence but changed the ordering of normalized and topological exports.

Highlights and analysis are generated automatically and may contain errors. Check the original source.