Paper Citation Record · LEDGER

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks

As of 21 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 2 inbound Pith citation observations for arXiv:2605.13214.

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

pith.paper-citation-record.v1
2605.13214 v2

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T21:55:21.464980Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-13T02:21:51.767054Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

31 of 31 outbound references displayed

verified exact10
verified fuzzy19
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation a198a014-46f7-4b1c-880c-045d532aa16b · outbound

This paper cites Backdoor Attacks and Defenses in Computer Vision Domain: A Survey.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Backdoor Attacks and Defenses in Computer Vision Domain: A Survey

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-30T22:05:06.204378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c417326f-2ad8-4623-8957-9e2650eeafa1 · outbound

This paper cites Complexity theoretic lower bounds for sparse principal component detection.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Complexity theoretic lower bounds for sparse principal component detection

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.885669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 333dfe8e-f95a-4702-a462-3ec4b5f9b9e1 · outbound

This paper cites Computational Lower Bounds for Sparse PCA.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Computational Lower Bounds for Sparse PCA

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-30T22:05:06.191896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4aa8008d-460b-4e7d-9bd3-0513baf95ae8 · outbound

This paper cites Brennan and Guy Bresler.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Brennan and Guy Bresler

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.883910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 75064d8e-e7c9-48e8-9101-124ddfa5d05e · outbound

This paper cites Data free backdoor attacks.Advances in Neural Information Processing Systems, 37:23881–23911.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Data free backdoor attacks.Advances in Neural Information Processing Systems, 37:23881–23911

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.887573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 27ded4e8-d35a-4e96-923d-4e58ad9de63f · outbound

This paper cites Wild patterns reloaded: A survey of machine learning security against training data poisoning.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Wild patterns reloaded: A survey of machine learning security against training data poisoning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.882209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 124845ea-196e-4d8e-a87e-1430e2d45705 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-30T22:05:06.207014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a3632e5a-0304-4377-a319-0833d480886a · outbound

This paper cites Unelicitable backdoors via cryptographic transformer circuits.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Unelicitable backdoors via cryptographic transformer circuits

Reference 8

Resolution: verified exact; doi, observed 2026-06-30T22:05:05.564833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2bfcecd9-0f53-4196-87bd-4dac18a2d930 · outbound

This paper cites Liu, Richard Peng, Maximilian Probst Gutenberg, and Sushant Sachdeva.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Liu, Richard Peng, Maximilian Probst Gutenberg, and Sushant Sachdeva

Reference 9

Resolution: malformed identifier; arxiv_id, observed 2026-06-30T22:05:06.189264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c493d7dd-a3ab-42fa-9fa9-fdbc428b6245 · outbound

This paper cites Planting Undetectable Backdoors in Machine Learning Models.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Planting Undetectable Backdoors in Machine Learning Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T22:05:06.186743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d2df0a3c-4b42-43c4-9c82-a0fa3cf09551 · outbound

This paper cites Borgwardt, Malte J.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Borgwardt, Malte J

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.874197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f9b674c3-a71b-408b-9d43-1bd3ab91b80d · outbound

This paper cites an unresolved cited work.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-07-07T15:33:53.880378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9269efc8-40dd-41aa-b5ea-2809724a6f18 · outbound

This paper cites Papakostas.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Papakostas

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.872453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3a9ad4da-185d-4c9c-94f8-acd4f7101e33 · outbound

This paper cites Concept backpropagation: An Explainable AI approach for visualising learned concepts in neural network models.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Concept backpropagation: An Explainable AI approach for visualising learned concepts in neural network models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-30T22:05:06.210500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dbb461ed-cb65-44ae-9ccd-2eb9cbee5028 · outbound

This paper cites Survey on backdoor attacks on deep learning: Current trends, categorization, applications, research challenges, and future prospects.IEEE Access.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Survey on backdoor attacks on deep learning: Current trends, categorization, applications, research challenges, and future prospects.IEEE Access

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.868567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1c54aec1-b553-4b18-942c-40d00ad4101d · outbound

This paper cites Deep residual learning for image recognition.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Deep residual learning for image recognition

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.850649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9f172da6-4131-4661-9b50-c87eb0025682 · outbound

This paper cites Handcrafted backdoors in deep neural networks.Advances in Neural Information Processing Systems, 35:8068–8080.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Handcrafted backdoors in deep neural networks.Advances in Neural Information Processing Systems, 35:8068–8080

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.864552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4ce950cb-d964-4b09-8683-a260ec4a4340 · outbound

This paper cites Injecting undetectable backdoors in obfuscated neural networks and language models.Advances in Neural Information Processing Systems, 37:21537–21571.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Injecting undetectable backdoors in obfuscated neural networks and language models.Advances in Neural Information Processing Systems, 37:21537–21571

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.866429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2efb1603-1716-4021-a41a-5a8e58e9586a · outbound

This paper cites Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav).

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.870662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fef51c70-6ece-4e50-b60c-b2a3585ca7af · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Adam: A Method for Stochastic Optimization

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-06-30T22:05:06.213000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1adf3f7d-691c-4965-b168-ede7622d80b0 · outbound

This paper cites Learning multiple layers of features from tiny images.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Learning multiple layers of features from tiny images

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.878527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 58b8a5fe-d82b-4ac5-b778-bf7cb3268999 · outbound

This paper cites Analyzing and editing inner mechanisms of backdoored language models.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Analyzing and editing inner mechanisms of backdoored language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.853370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fb7a7577-27bf-4694-8941-9d2e2461dfa5 · outbound

This paper cites Fine-pruning: Defending against backdooring attacks on deep neural networks.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Fine-pruning: Defending against backdooring attacks on deep neural networks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.860966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4b9b6285-ecf6-4d96-89e9-d837048a9403 · outbound

This paper cites Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning.Journal of Machine Learning Research, 22(165):1–73.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning.Journal of Machine Learning Research, 22(165):1–73

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.854911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5f4ac7eb-42ae-41e8-808b-3ac28c014786 · outbound

This paper cites Random features for large-scale kernel machines.Advances in neural information processing systems, 20.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Random features for large-scale kernel machines.Advances in neural information processing systems, 20

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.856920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b53eabf7-20e4-4599-b94a-a4cd922127d7 · outbound

This paper cites an unresolved cited work.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Unresolved cited work

Reference 26

Resolution: verified exact; doi, observed 2026-06-30T22:05:05.559652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 13b3cbca-5588-460c-a7fe-ed880e340d80 · outbound

This paper cites Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-30T22:05:06.195240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cfb9e1a0-dbd9-432d-af33-ef74fe24651a · outbound

This paper cites Empirical Analysis of the Hessian of Over-Parametrized Neural Networks.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Empirical Analysis of the Hessian of Over-Parametrized Neural Networks

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-06-30T22:05:06.201330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 71293396-a896-4cec-b714-657aee720b2d · outbound

This paper cites Empirical analysis of the hessian of over-parametrized neural networks.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Empirical analysis of the hessian of over-parametrized neural networks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.862786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 93d55be1-d10d-4810-8b51-3b3f2fb99161 · outbound

This paper cites Neural cleanse: Identifying and mitigating backdoor attacks in neural networks.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Neural cleanse: Identifying and mitigating backdoor attacks in neural networks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.876050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0f36aeab-1985-4095-a1ac-360c7958d34e · outbound

This paper cites Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification.Scientific data, 10(1):41.

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification.Scientific data, 10(1):41

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T15:33:53.859004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 0afc8167-05ba-4d46-8a8d-765571506b13 · inbound

Statistically Undetectable Backdoors in Deep Neural Networks cites this paper.

Statistically Undetectable Backdoors in Deep Neural Networks Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-07-13T02:29:15.222215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d284d044-66e6-4657-a827-27c8a7b5b83d · inbound

Statistically Undetectable Backdoors in Deep Neural Networks cites this paper.

Statistically Undetectable Backdoors in Deep Neural Networks Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-13T02:21:51.767054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.