Pith Number

pith:JNPW5ZCV

pith:2026:JNPW5ZCVLQFBMNE23LTTCL7OVL

not attested not anchored not stored refs resolved

Speed Kills: Exploring Confused Deputy Attacks Through Edge AI Accelerators

Aravind Kumar Machiry, Datta Manikanta Sri Hari Danduri

AI accelerators on edge devices can be tricked by apps into performing privileged operations outside OS control.

arxiv:2605.17707 v1 · 2026-05-18 · cs.CR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{JNPW5ZCVLQFBMNE23LTTCL7OVL}

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

CDA is feasible on six out of the seven AIAs, impacting over 128 System On Chips (SOCs) and over 100 million devices.

C2weakest assumption

The DeputyHunt framework, combining LLM-assisted dynamic and static analysis, correctly identifies exploitable confused deputy paths without substantial false positives or missed cases on the tested accelerators.

C3one line summary

An empirical security study shows confused deputy attacks are practical on most edge AI accelerators via a new LLM-assisted analysis framework, with vendor-confirmed impact on over 100 million devices.

References

152 extracted · 152 resolved · 0 Pith anchors

[1] Ai-powered mobile applications: Revolutionizing user inter- action through intelligent features and context-aware services, 2023

[2] Ai-powered laptop companions: Bridging the human-machine gap, 2024

[3] Empowering edge intelligence: A comprehensive survey on on-device ai models, 2025

[4] Ai- based autonomous driving assistance system, 2021

[5] A survey on the optimization of neural network accelerators for micro-ai on-device inference, 2021

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:04:53.769666Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4b5f6ee4555c0a16349adae7312feeaafcd340145d157f7bee39cb65a28613c2

Aliases

arxiv: 2605.17707 · arxiv_version: 2605.17707v1 · doi: 10.48550/arxiv.2605.17707 · pith_short_12: JNPW5ZCVLQFB · pith_short_16: JNPW5ZCVLQFBMNE2 · pith_short_8: JNPW5ZCV

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/JNPW5ZCVLQFBMNE23LTTCL7OVL \
  | 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: 4b5f6ee4555c0a16349adae7312feeaafcd340145d157f7bee39cb65a28613c2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4fbc471209c6cad64cd6bbf3bf0cb2d3ac814263fdcd8371fec90506f6be1c66",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-05-18T00:04:51Z",
    "title_canon_sha256": "c4488fc7622779240b0c058d932caf06560075262822089783a00b8a2d905b77"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.17707",
    "kind": "arxiv",
    "version": 1
  }
}