Pith Number

pith:EMQ7WYLF

pith:2026:EMQ7WYLFTUKJYMWXXJ2UJT63BF

not attested not anchored not stored refs pending

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

Jinyu Gu, Lixiang Wang, Yinpeng Wu, Yitong Chen, Yubin Xia, Zhichao Hua

FlexServe allows ARM TrustZone to protect mobile LLM inference by switching memory and NPU modes on demand, cutting time to first token by over 10x versus rigid baselines.

arxiv:2603.09046 v3 · 2026-03-10 · cs.CR · cs.LG · cs.OS

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EMQ7WYLFTUKJYMWXXJ2UJT63BF}

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

FlexServe achieves an average 10.05× speedup in Time to First Token (TTFT) compared to the strawman, and an average 2.44× TTFT speedup compared to an optimized strawman with pipeline and secure NPU enabled. For multi-model agent workflows, the end-to-end speedup is up to 24.30× and 4.05× compared to the strawman and optimized strawman, respectively.

C2weakest assumption

The flexible switching between protected and unprotected modes for memory and NPU does not introduce new security vulnerabilities or significant unmeasured overheads beyond the reported prototype benchmarks.

C3one line summary

FlexServe achieves up to 10x faster time-to-first-token for secure LLM inference on mobile devices by using flexible resource isolation in TrustZone compared to standard approaches.

Cited by

1 paper in Pith

SoK: Attack and Defense Landscape of Mobile On-device AI Systems

Receipt and verification

First computed	2026-07-03T00:16:53.070116Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2321fb61659d149c32d7ba7544cfdb09722cf9d742cfb062e82cc5fc51bec945

Aliases

arxiv: 2603.09046 · arxiv_version: 2603.09046v3 · doi: 10.48550/arxiv.2603.09046 · pith_short_12: EMQ7WYLFTUKJ · pith_short_16: EMQ7WYLFTUKJYMWX · pith_short_8: EMQ7WYLF

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/EMQ7WYLFTUKJYMWXXJ2UJT63BF \
  | 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: 2321fb61659d149c32d7ba7544cfdb09722cf9d742cfb062e82cc5fc51bec945

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f0f6015630047f5dd504b5c140c4b48f8d9e104b7d3f16d8d557b5bc563535f5",
    "cross_cats_sorted": [
      "cs.LG",
      "cs.OS"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-03-10T00:31:25Z",
    "title_canon_sha256": "f38ae1944cb60340e583f1ac9d2ee6b87b47688d41e4a10f9415ea7685367f7b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.09046",
    "kind": "arxiv",
    "version": 3
  }
}