Paper Citation Record · LEDGER

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models

As of 17 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 1 inbound Pith citation observation for arXiv:2411.09540.

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

pith.paper-citation-record.v1
2411.09540 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T20:37:30.420221Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:21:42.130463Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T18:16:14.067578Z

Reference resolution

22 of 22 outbound references displayed

verified exact0
verified fuzzy13
unresolved8
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2ce0235c-986a-4280-a380-bb6f62527311 · outbound

This paper cites Exploring Visual Prompts for Adapting Large-Scale Models.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Exploring Visual Prompts for Adapting Large-Scale Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T20:37:30.314630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3239486f-351a-4bcd-a086-d671c8895aa2 · outbound

This paper cites Sentinet: Detecting localized universal attacks against deep learning systems.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Sentinet: Detecting localized universal attacks against deep learning systems

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.776428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 64d2809e-eede-4e73-913d-ffd7378cdd9c · outbound

This paper cites Ahmed Salem, Rui Wen, Michael Backes, Shiqing Ma, and Yang Zhang.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Ahmed Salem, Rui Wen, Michael Backes, Shiqing Ma, and Yang Zhang

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T20:37:30.356662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29733a22-01fd-436a-86eb-be433844e126 · outbound

This paper cites Label-Consistent Backdoor Attacks.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Label-Consistent Backdoor Attacks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T20:37:30.362103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 420f4d28-13c0-464d-af54-b4d40012af5b · outbound

This paper cites Bppattack: Stealthy and efficient trojan attacks against deep neural networks via image quantization and contrastive adversarial learning.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Bppattack: Stealthy and efficient trojan attacks against deep neural networks via image quantization and contrastive adversarial learning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.716007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1b775c48-542a-44ab-b238-19f3177d5984 · outbound

This paper cites Section A details the implementation and configurations of the experiments.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Section A details the implementation and configurations of the experiments

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.700797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e8c55985-593c-41bb-a148-09f1180a73f6 · outbound

This paper cites • Poison rate: The proportion of training data with the trigger pattern.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models • Poison rate: The proportion of training data with the trigger pattern

Reference 13

Resolution: malformed identifier; raw_fallback, observed 2026-08-12T20:37:30.684951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fd0e8fda-b61f-4706-ba54-347ff3ccf7ce · outbound

This paper cites (2018) 0.952 0.047 0.952 0.115 0.240 0.952 0.551 SS (Tran et al.,.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models (2018) 0.952 0.047 0.952 0.115 0.240 0.952 0.551 SS (Tran et al.,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.620980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 017a04d4-5af8-45fd-9e3e-f275ef69be5d · outbound

This paper cites an unresolved cited work.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-12T20:37:30.603129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dbdc7220-82d1-4e20-9629-17a8a3cb3cc7 · outbound

This paper cites We analyze the impact of the reserved clean dataset size (DS) on BPROM’s performance.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models We analyze the impact of the reserved clean dataset size (DS) on BPROM’s performance

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.587650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c7f342f8-7134-4a92-8ad9-d12a98fd607c · outbound

This paper cites 4https://github.com/vtu81/backdoor-toolbox 16 This paper has been accepted by IEEE/IFIP DSN 2025 • SCAn (Tang et al., 2021): Threshold for abnormal score = 0.5.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models 4https://github.com/vtu81/backdoor-toolbox 16 This paper has been accepted by IEEE/IFIP DSN 2025 • SCAn (Tang et al., 2021): Threshold for abnormal score = 0.5

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.668772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 39f380e8-1769-4e33-90e8-ca1fc12f8453 · outbound

This paper cites (2018) cifar10 0.5002 0.3902 0.3745 0.5145 0.6154 0.3801 0.3977 0.4532 gtsrb 0.4925 0.4987 0.4925 0.4925 0.4966 0.4961 0.4929 0.4945 SCAn (Tang et al.,.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models (2018) cifar10 0.5002 0.3902 0.3745 0.5145 0.6154 0.3801 0.3977 0.4532 gtsrb 0.4925 0.4987 0.4925 0.4925 0.4966 0.4961 0.4929 0.4945 SCAn (Tang et al.,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.571641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1f56c14e-1da1-42a8-b1ba-4013e47b555b · outbound

This paper cites The same meta-model is also used to classify clean (green dots) and Adap-Blend-infected models (red dots) Qi et al.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models The same meta-model is also used to classify clean (green dots) and Adap-Blend-infected models (red dots) Qi et al

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.555696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9da795cc-2f24-4dc3-957b-b26e557020f7 · outbound

This paper cites (2018) cifar10 0.3877 0.3745 0.3753 0.2747 0.3749 0.3749 0.3913 0.3648 gtsrb 0.4961 0.4925 0.4946 0.4987 0.4925 0.4925 0.4925 0.4942 SCAn (Tang et al.,.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models (2018) cifar10 0.3877 0.3745 0.3753 0.2747 0.3749 0.3749 0.3913 0.3648 gtsrb 0.4961 0.4925 0.4946 0.4987 0.4925 0.4925 0.4925 0.4942 SCAn (Tang et al.,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.539428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a3e35a1a-cfca-43b1-a615-433712bd7307 · outbound

This paper cites an unresolved cited work.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Unresolved cited work

Reference 2011

Resolution: unresolved; raw_fallback, observed 2026-08-12T20:37:30.653468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 72edb3fb-1a3b-43b6-afcf-7862d5da19eb · outbound

This paper cites Neural attention distillation: Erasing backdoor triggers from deep neural networks.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Neural attention distillation: Erasing backdoor triggers from deep neural networks

Reference 2015

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.746427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 183ac8c2-5ae3-4841-8de3-6e99d87cdb42 · outbound

This paper cites Ranasinghe, and Hyoungshick Kim.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Ranasinghe, and Hyoungshick Kim

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.761130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 984e727b-ff2b-4839-9801-c3b3211acf0f · outbound

This paper cites To investigate the impact of inconsistency between the numbers of classes in DS and DT , we conducted experiments using CIFAR-100 as DS and STL-10 as DT.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models To investigate the impact of inconsistency between the numbers of classes in DS and DT , we conducted experiments using CIFAR-100 as DS and STL-10 as DT

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.637455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 18c59da8-f783-4ed7-840a-5f546082ef44 · outbound

This paper cites Deep Residual Learning for Image Recognition.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Deep Residual Learning for Image Recognition

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-12T20:37:30.336234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63f8b906-cb34-4d5c-94f6-9fac315d5547 · outbound

This paper cites an unresolved cited work.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Unresolved cited work

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-12T20:37:30.346601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aad93cd-30a4-4d1c-aaf2-f4d8553ad722 · outbound

This paper cites Revisiting the assump- tion of latent separability for backdoor defenses.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Revisiting the assump- tion of latent separability for backdoor defenses

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:37:30.731059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5bfc539d-9e3e-49c2-a3ce-73e486e747c2 · outbound

This paper cites Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning.

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T20:37:30.320604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2ea066c2-1397-45ab-8bca-43269cf8597d · inbound

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models cites this paper.

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models

Reference 59

Resolution: verified exact; local_arxiv, observed 2026-08-15T14:23:33.257433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.