Pith. sign in

Paper Citation Record · LEDGER

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks

As of 10 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2505.19821.

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

pith.paper-citation-record.v1
2505.19821 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:11:59.185492Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

27 of 27 outbound references displayed

  • verified exact2
  • verified fuzzy8
  • unresolved17
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ad6de900-879a-4944-a5f1-d9ea0e010f8e · outbound

This paper cites Deep learning in medical image analysis,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Deep learning in medical image analysis,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:57.397730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:57.397730Z digest=sha256:d936b0709fd1a75499d201ef2a615f1760bf7231185652113d3e081e5113b925

Observation b3145e42-2d2e-4fd7-9da0-189926909aa7 · outbound

This paper cites Deep learning for finance: deep portfolios,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Deep learning for finance: deep portfolios,

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:12:00.766112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:57.446054Z digest=sha256:b2d44c20539b03f429ae4f6db37207dec9fef00062959e46881a7f056e576dec

Observation 4b5003c5-c0cc-4139-b9df-93c763a9ee47 · outbound

This paper cites Badnets: Evaluating backdooring attacks on deep neural networks,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Badnets: Evaluating backdooring attacks on deep neural networks,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:57.491615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:57.491615Z digest=sha256:3430588935daa9c1354c383beeeca987938adbb4c88ac2e340a82f29ddf334ae

Observation 389ee68a-d481-41db-9af2-59e94a60f572 · outbound

This paper cites Narcissus: A practical clean-label backdoor attack with limited information,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Narcissus: A practical clean-label backdoor attack with limited information,

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:57.545287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:57.545287Z digest=sha256:5fd03f83b29acf640f168002b973453e06cdbb0188b8891373c57e8ebcfdd51d

Observation e4b78962-010c-44fa-9351-c3e287582141 · outbound

This paper cites Not all samples are born equal: Towards effective clean-label backdoor attacks,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Not all samples are born equal: Towards effective clean-label backdoor attacks,

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:12:00.672188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:57.610048Z digest=sha256:991615dc116a91f02a96d5bce38ef9d57004fa9c7e74bf187811020c29b60406

Observation 047cef08-6602-42b5-a570-0a2fd71b4d70 · outbound

This paper cites NSML: Meet the MLaaS platform with a real-world case study.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks NSML: Meet the MLaaS platform with a real-world case study

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:57.671059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:57.671059Z digest=sha256:2ae79603e9c622fdaec53542c5c448eba3497e959920baa4c24b73e3983f3489

Observation 81bfc361-7929-4265-bacd-daded8402acd · outbound

This paper cites Mlaas: Machine learning as a service,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Mlaas: Machine learning as a service,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:12:00.595730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:57.726842Z digest=sha256:0efc791aecbd37f225636473ddc73cbbfdf1a7eff5b2ffdd28628c992dcf15e1

Observation a4450457-6da1-4735-ab5d-085849535acc · outbound

This paper cites IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:57.776639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:57.776639Z digest=sha256:a09708ac4f5c1dc9b2ed12afcec04a3929505962129a9e57372922aedf444784

Observation 22630bca-1b93-4477-a2c0-ac7d40a216e8 · outbound

This paper cites SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:57.820012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:57.820012Z digest=sha256:fda7f3ebd18d0e21a921e4578bdb54bc5937eb768c22061a6fd91cbd909d4a59

Observation bd9ae334-048c-4779-82df-592265937928 · outbound

This paper cites The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-08-07T14:11:59.655002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:57.879116Z digest=sha256:2686b905df5fb4eaeb2480492c890013cada2c520b3cedcdceece2a16237b037

Observation df1811f9-bfb5-4c7b-9da5-14dbc1274a1e · outbound

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

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:57.957848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:57.957848Z digest=sha256:5fd004cb8528958f77e755d46029319f41abb5922f058c40a82463c80ce830f7

Observation 36132e57-dfe7-450a-abeb-55c7d7304222 · outbound

This paper cites WaNet -- Imperceptible Warping-based Backdoor Attack.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks WaNet -- Imperceptible Warping-based Backdoor Attack

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.006307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.006307Z digest=sha256:9f92394688e4318e05502000515ad7f93c8fa24cdc60b6c135a818b3642c9f90

Observation d5856a2b-89d2-4326-91d8-e8813c6c7be5 · outbound

This paper cites Trojaning attack on neural networks,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Trojaning attack on neural networks,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.052339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.052339Z digest=sha256:b3c3d5abe07290dbb80b00aa9a53a082c677032022405fc63c7c20e23c7fe721

Observation 34360cae-c940-43ab-8aef-7368e1aa07cc · outbound

This paper cites Label-Consistent Backdoor Attacks.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Label-Consistent Backdoor Attacks

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.123910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.123910Z digest=sha256:c04e77e16e00dda76fcdefcf7c62d155cd05f47f208634fd97aa77ad0d97c6ae

Observation 86ca8183-19e6-4c01-8c8c-e46490ca0941 · outbound

This paper cites Input-aware dynamic backdoor attack,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Input-aware dynamic backdoor attack,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:12:00.506553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:58.183890Z digest=sha256:bfb977b43af1c08218624430e84816cc2c64c10d57f2a6f62b9a3483275109dc

Observation cfa761d0-1fd1-4979-8b09-d649caa9a692 · outbound

This paper cites A new backdoor attack in cnns by training set corruption without label poisoning,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks A new backdoor attack in cnns by training set corruption without label poisoning,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:12:00.416988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:58.241276Z digest=sha256:80b85e1932ccd8dded974569f84c8c246489333ef2fe87c1b682e219322e7424

Observation 5100b151-9055-4006-9575-601c77c37dba · outbound

This paper cites Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

Reference 17

Resolution
verified exact
local_arxiv, observed 2026-08-07T14:11:59.445514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:58.291789Z digest=sha256:17484051ef4b5f9587cb0bb57a0f857a32a619b97fe9fc7ef370b1b33f323269

Observation 86c21b19-0312-4782-8e76-bffb03f042de · outbound

This paper cites Computation and data effi- cient backdoor attacks,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Computation and data effi- cient backdoor attacks,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:12:00.323161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:58.368570Z digest=sha256:650ef1221aed80a4e9105cf021f9b5b0e1b39f3bd059b334a03aa276af434469

Observation fcf94479-d62f-41f3-b1e3-8f9cfb059c44 · outbound

This paper cites Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.445299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.445299Z digest=sha256:21230556cfa343ed6e1b6eda4cfe82294c76a677c6b8ed513d7a5e18e37ab481

Observation 6afce261-261e-4024-93a1-0d58cc9f5c73 · outbound

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

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Neural cleanse: Identifying and mitigating backdoor attacks in neural networks,

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.538697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.538697Z digest=sha256:fe1c82080d252a7d9ac2ce1c6c358641d6ec039ae68beebab9606154fb34c0e6

Observation 336a696f-893d-4b98-b63c-52aab7708384 · outbound

This paper cites Strip: A defence against trojan attacks on deep neural networks,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Strip: A defence against trojan attacks on deep neural networks,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:12:00.085385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:58.616284Z digest=sha256:e1cbd1d02f1bc943628147499c427fbd57bb44c36102270ee8f304e96b14c744

Observation af159260-2b04-4abd-b33d-15216890b047 · outbound

This paper cites Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.707322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.707322Z digest=sha256:390e5bec9efd454de7d1cc8ec5f0c5d3321c779a0a53975d713676e903ba8c72

Observation affd1e7a-6f66-4036-91de-bd42c82a74ed · outbound

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

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Fine-pruning: Defending against backdooring attacks on deep neural networks,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:11:59.895448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T14:11:58.812933Z digest=sha256:d2e856d5e4975d3f556fd54d40099da5bfb79490a533c37e1efbf15d707a9d1e

Observation ec39fd5c-a185-407f-81df-dbbb7a29b8fb · outbound

This paper cites Deep residual learning for image recognition,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Deep residual learning for image recognition,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.898975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.898975Z digest=sha256:7a721dda34d883f25e07e6b05129c22fe7da3396541aa3ae53f46f78709d0d06

Observation 7d21f168-5965-41fa-b0e9-4ef9ad1fbf77 · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.908480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.908480Z digest=sha256:df07a01f2901ab41dcf72710ccc052cd4074b50f014853473f748ba82b4304ca

Observation 05909ba8-a053-4821-984b-7fef5dbf7f64 · outbound

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

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Learning multiple layers of features from tiny images,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:58.985511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:58.985511Z digest=sha256:fc6170989b174711b56f14ca9472971e9892f6cbbd18b1a885399c43592847d1

Observation 5f081565-e2cb-4374-8780-6f241e6ff8dd · outbound

This paper cites Tiny imagenet visual recognition challenge,.

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks Tiny imagenet visual recognition challenge,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T14:11:59.185492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:11:59.185492Z digest=sha256:a71330a61054fbdc9273b87a78a11e284f981534a367118b21bb3783ba2c35ec

Pith citing papers

No inbound Pith citation observations are available.