Paper Citation Record · LEDGER

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis

As of 9 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2606.14427.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2606.14427 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-12T14:06:47.857777Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

12 of 12 outbound references displayed

verified exact0
verified fuzzy0
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b3938e1a-a69e-4f35-8376-ec29a2872ad9 · outbound

This paper cites An evaluation of edge tpu accelerators for convolutional neural networks,.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis An evaluation of edge tpu accelerators for convolutional neural networks,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db55d524-59de-4311-996c-74dc78bf3002 · outbound

This paper cites Xnor neural engine: A hardware accelerator ip for 21.6-fj/op binary neural network inference,.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis Xnor neural engine: A hardware accelerator ip for 21.6-fj/op binary neural network inference,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f81d80e-b45d-47e3-8046-5c86a8ad210b · outbound

This paper cites An Empirical Study of the Influence of Adversarial Fine-Tuning on Compressed Neural Networks.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis An Empirical Study of the Influence of Adversarial Fine-Tuning on Compressed Neural Networks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c93c8359-5a9f-4b1f-9fe3-64d490fe550e · outbound

This paper cites David and goliath: An empirical evaluation of attacks and defenses for qnns at the deep edge,.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis David and goliath: An empirical evaluation of attacks and defenses for qnns at the deep edge,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7b81524-ae33-46f0-b95d-ee120e0b40df · outbound

This paper cites Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d47579e4-ccb6-463d-854b-cf5d7049a346 · outbound

This paper cites Prada: protecting against dnn model stealing attacks,.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis Prada: protecting against dnn model stealing attacks,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a3e9d38-ce59-4c4b-a5e8-a58cbac4fde5 · outbound

This paper cites Knockoff nets: Stealing function- ality of black-box models,.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis Knockoff nets: Stealing function- ality of black-box models,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bb9d968-179d-421c-bcb5-f165670cf340 · outbound

This paper cites Copycat cnn: Stealing knowledge by persuading confession with random non-labeled data,.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis Copycat cnn: Stealing knowledge by persuading confession with random non-labeled data,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fa0aaf9-1cb5-45be-9346-41cfdfe39fde · outbound

This paper cites MLPerf Tiny Benchmark.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis MLPerf Tiny Benchmark

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12fb4f4c-5048-4d0e-9ed1-12b214c4389a · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis Explaining and Harnessing Adversarial Examples

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 738eb42e-0e50-4032-ae27-fa8e1594153a · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6f084ff-dac2-4ac7-8c52-5cc71819e445 · outbound

This paper cites RobustBench: a standardized adversarial robustness benchmark.

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis RobustBench: a standardized adversarial robustness benchmark

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T14:06:47.857777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.