Pith Number

pith:VICWIOCY

pith:2026:VICWIOCY74WXRCUI2CIXDMO6DR

not attested not anchored not stored refs pending

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

Bo Li, Chaowei Xiao, Cong Wang, Hanxun Huang, James Bailey, Jianping Wang, Jiayu Li, Jingjing Chen, Jun Sun, Kun Wang, Ming Wen, Qi Zhang, Ran He, Sarah Erfani, Tao Gui, Tiehua Zhang, Xiang Zheng, Xiao Li, Xinfeng Li, Xingjun Ma, Xin Wang, Xinyu Xia, Xipeng Qiu, Xuanjing Huang, Xun Gong, Ye Sun, Yifeng Gao, Yige Li, Yi Liu, Yixin Cao, Yixu Wang, Yu-Gang Jiang, Yunhan Zhao, Yutao Wu, Zhineng Chen, Zhipeng Wei, Zixing Chen, Zuxuan Wu

Embodied AI requires safety measures that span the full pipeline from perception and planning to physical action and human interaction.

arxiv:2605.02900 v2 · 2026-03-28 · cs.CR · cs.AI · cs.CV · cs.RO

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VICWIOCY74WXRCUI2CIXDMO6DR}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

This survey provides a comprehensive and structured review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline, from perception and cognition to planning, action and interaction, and agentic system, while revealing several overlooked challenges.

C2weakest assumption

The assumption that the selection and synthesis of over 400 papers accurately captures the current state of the field and that the proposed multi-level taxonomy meaningfully unifies previously fragmented research lines.

C3one line summary

The survey organizes over 400 papers on embodied AI safety into a multi-level taxonomy and flags overlooked issues such as fragile multimodal fusion and unstable planning under jailbreaks.

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-26T02:03:14.108584Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

aa05643858ff2d788a88d09171b1de1c702e246d4ada8313d05d54db1da9e1b2

Aliases

arxiv: 2605.02900 · arxiv_version: 2605.02900v2 · doi: 10.48550/arxiv.2605.02900 · pith_short_12: VICWIOCY74WX · pith_short_16: VICWIOCY74WXRCUI · pith_short_8: VICWIOCY

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/VICWIOCY74WXRCUI2CIXDMO6DR \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: aa05643858ff2d788a88d09171b1de1c702e246d4ada8313d05d54db1da9e1b2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "95677cc6f92838b71d5d662528f81f56195befbeae360d181fa791961da08934",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV",
      "cs.RO"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-03-28T13:21:44Z",
    "title_canon_sha256": "13530b6cd35985836d725a6950c5d0acaa6e3f0846ee747cd820daf0c872bf96"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.02900",
    "kind": "arxiv",
    "version": 2
  }
}