Pith. sign in

REVIEW 2 cited by

Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.15699 v3 pith:TSTMMUGK submitted 2025-04-22 cs.AI

Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation

classification cs.AI
keywords moderationembodiedagentsinputsafetybenchmarkbenchmarksdesigned
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Embodied agents exhibit immense potential across a multitude of domains, making the assurance of their behavioral safety a fundamental prerequisite for their widespread deployment. However, existing research predominantly concentrates on the security of general large language models, lacking specialized methodologies for establishing safety benchmarks and input moderation tailored to embodied agents. To bridge this gap, this paper introduces a novel input moderation framework, meticulously designed to safeguard embodied agents. This framework encompasses the entire pipeline, including taxonomy definition, dataset curation, moderator architecture, model training, and rigorous evaluation. Notably, we introduce EAsafetyBench, a meticulously crafted safety benchmark engineered to facilitate both the training and stringent assessment of moderators specifically designed for embodied agents. Furthermore, we propose Pinpoint, an innovative prompt-decoupled input moderation scheme that harnesses a masked attention mechanism to effectively isolate and mitigate the influence of functional prompts on moderation tasks. Extensive experiments conducted on diverse benchmark datasets and models validate the feasibility and efficacy of the proposed approach. The results demonstrate that our methodologies achieve an impressive average detection accuracy of 94.58%, surpassing the performance of existing state-of-the-art techniques, alongside an exceptional moderation processing time of merely 0.002 seconds per instance.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space

    cs.AI 2026-07 conditional novelty 6.0

    Content danger and physical danger form separable hidden-state signals in LLMs, and a single-layer logistic probe (PRISM) detects both at lower false-positive rates than LLM judges or text guardrails.

  2. Position: Embodied AI Requires a Privacy-Utility Trade-off

    cs.AI 2026-05 unverdicted novelty 4.0

    Embodied AI requires treating privacy as a lifecycle architectural constraint rather than a stage-local feature, addressed via the proposed SPINE framework with a multi-criterion privacy classification matrix.