Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning | Paper Citation Record

Observation a2a32e22-414b-43e9-9449-bc4a38f944f2 · outbound

This paper cites Masktune: Mitigating spurious correlations by forcing to explore.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Masktune: Mitigating spurious correlations by forcing to explore

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.943058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6fb2a055-f8b4-4117-92af-e4c1b6065045 · outbound

This paper cites Rademacher and gaussian complexities: Risk bounds and structural results.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Rademacher and gaussian complexities: Risk bounds and structural results

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.932439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 489f0ba7-bab9-4cbd-bf63-fc3d5b08379c · outbound

This paper cites Mixmatch: A holistic approach to semi-supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Mixmatch: A holistic approach to semi-supervised learning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.921004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 27cbc744-bec7-45df-b979-da1a0f46f356 · outbound

This paper cites Remix- match: Semi-supervised learning with distribution alignment and augmentation anchoring.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Remix- match: Semi-supervised learning with distribution alignment and augmentation anchoring

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.909685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 045313fa-bd5b-4039-8e5c-d4433d2c4367 · outbound

This paper cites Poisoning the unlabeled dataset of {Semi- Supervised} learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Poisoning the unlabeled dataset of {Semi- Supervised} learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.899715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cab99dba-d34d-4cbb-bbd6-a98af6521b07 · outbound

This paper cites Semi-supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Semi-supervised learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.888986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b068910c-5f85-4f0e-89e8-ae43c8d73632 · outbound

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

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T18:12:20.852645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5309c973-98ce-408a-b3bf-17ab16a854fb · outbound

This paper cites Softmatch: Addressing the quantity-quality trade-off in semi-supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Softmatch: Addressing the quantity-quality trade-off in semi-supervised learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.878841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 500ba90f-db4a-4654-ae2d-bb44c35185a0 · outbound

This paper cites A practical clean-label backdoor attack with limited information in vertical federated learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning A practical clean-label backdoor attack with limited information in vertical federated learning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.869956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6f848af6-8dea-408e-976c-f794bb2cff0c · outbound

This paper cites An analysis of single-layer networks in unsupervised feature learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning An analysis of single-layer networks in unsupervised feature learning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.859120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e238fa46-0a7b-4b65-8e89-d5c1021974fe · outbound

This paper cites Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-08T18:12:21.118184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation aae6559a-be71-4d33-8bd2-286455ea2435 · outbound

This paper cites Black-box detection of back- door attacks with limited information and data.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Black-box detection of back- door attacks with limited information and data

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.847234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 87977a2b-c3ab-4b85-b92d-f661f1d3bc32 · outbound

This paper cites Learning with multiple complementary labels.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Learning with multiple complementary labels

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.835243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 216b2807-7fc5-492c-9b61-de941a6a3906 · outbound

This paper cites Unbiased risk es- timator to multi-labeled complementary label learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Unbiased risk es- timator to multi-labeled complementary label learning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.823751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c59625cd-a46f-4bc0-b668-8e31d46e2b43 · outbound

This paper cites Complementary to multiple labels: A correlation-aware correction approach.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Complementary to multiple labels: A correlation-aware correction approach

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.812880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e149081e-1710-439b-9a0c-b7b3900fcbe9 · outbound

This paper cites Identifying vulner- abilities in the machine learning model supply chain.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Identifying vulner- abilities in the machine learning model supply chain

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.803021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b0e70138-9fcf-4e2c-b0f8-d2037701f7f3 · outbound

This paper cites Safe deep semi-supervised learning for unseen-class unlabeled data.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Safe deep semi-supervised learning for unseen-class unlabeled data

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.791847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation caf4f58b-9aad-4bd8-913a-af94e79a4143 · outbound

This paper cites Robust semi-supervised learning when not all classes have labels.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Robust semi-supervised learning when not all classes have labels

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.780152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 19666faf-5a24-4eb8-a15d-9a10b576465b · outbound

This paper cites Theoretical foundations of gaussian con- volution by extended box filtering.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Theoretical foundations of gaussian con- volution by extended box filtering

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.764974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0a6d037f-be2e-407b-967b-29e16d338dd1 · outbound

This paper cites Learning from complementary labels.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Learning from complementary labels

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.751128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0eef6c3c-d734-48d5-99d1-46007fa6b94e · outbound

This paper cites Bidirectional adaptation for ro- bust semi-supervised learning with inconsistent data distri- butions.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Bidirectional adaptation for ro- bust semi-supervised learning with inconsistent data distri- butions

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.737653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e0fb3a5b-eb5b-4347-a82b-2278ea0fcc98 · outbound

This paper cites Learn- ing multiple layers of features from tiny images.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Learn- ing multiple layers of features from tiny images

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.724858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c8e1d231-df8c-4f84-9983-18e15866fb7d · outbound

This paper cites Pseudo-label: The simple and effi- cient semi-supervised learning method for deep neural net- works.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Pseudo-label: The simple and effi- cient semi-supervised learning method for deep neural net- works

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.713273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 61d5c185-0ce1-4ecd-b35e-ee8686fc23c9 · outbound

This paper cites Instant: Semi-supervised learning with instance-dependent thresholds.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Instant: Semi-supervised learning with instance-dependent thresholds

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.701810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 927704e5-f824-4a94-bab7-d66679778351 · outbound

This paper cites Semireward: A general re- ward model for semi-supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Semireward: A general re- ward model for semi-supervised learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.690537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 14db541b-b9a3-431e-8618-7cdc1e9e5d09 · outbound

This paper cites Anti-backdoor learning: Training clean models on poisoned data.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Anti-backdoor learning: Training clean models on poisoned data

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.678285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d1cf3460-5fe3-4d2d-9e6a-403b44cc39cf · outbound

This paper cites Neural attention distillation: Erasing back- door triggers from deep neural networks.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Neural attention distillation: Erasing back- door triggers from deep neural networks

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.667420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f5a6fa26-aaa9-4d4b-a5f9-ac6ce5578c64 · outbound

This paper cites Back- door learning: A survey.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Back- door learning: A survey

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.656229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7b3a2c35-6284-4dfc-9a1e-22d92735d14b · outbound

This paper cites Towards making unlabeled data never hurt.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Towards making unlabeled data never hurt

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.644800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1b2f84f2-95a2-424c-83e6-71d2d4bb8cc5 · outbound

This paper cites Towards safe weakly supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Towards safe weakly supervised learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.632056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8b91564b-21a6-40cf-a5e9-73ef0d67ceac · outbound

This paper cites Iomatch: Simplifying open-set semi-supervised learning with joint in- liers and outliers utilization.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Iomatch: Simplifying open-set semi-supervised learning with joint in- liers and outliers utilization

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.614011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fbd74ea9-1e01-4fa4-9f3f-9923d5428a7f · outbound

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

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Fine- pruning: Defending against backdooring attacks on deep neural networks

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.601038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3dca801e-0cee-4c15-9c33-f2e7a6490939 · outbound

This paper cites Beating backdoor attack at its own game.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Beating backdoor attack at its own game

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.588449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 986acceb-976e-4f30-baa5-2aba97ab2732 · outbound

This paper cites Iterative reclassification procedure for constructing an asymptotically optimal rule of allocation in discriminant analysis.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Iterative reclassification procedure for constructing an asymptotically optimal rule of allocation in discriminant analysis

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.577226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation badcaf2d-32be-4104-899e-b8b22bf4f051 · outbound

This paper cites Foundations of machine learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Foundations of machine learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.567094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9c232269-c4bd-4c27-b3dc-7f9b46d4b05e · outbound

This paper cites Reading digits in natural images with unsupervised feature learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Reading digits in natural images with unsupervised feature learning

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.556026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9de0b0cc-fdca-4d9d-b62f-32b2f8d69628 · outbound

This paper cites Hidden trigger backdoor attacks.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Hidden trigger backdoor attacks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.543869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 39df8120-673f-435f-9741-2be47ad58584 · outbound

This paper cites Probability of error of some adaptive pattern-recognition machines.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Probability of error of some adaptive pattern-recognition machines

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.532901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d3901200-af71-4081-9d88-087e6d0df028 · outbound

This paper cites The perils of learning from unlabeled data: Backdoor attacks on semi-supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning The perils of learning from unlabeled data: Backdoor attacks on semi-supervised learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.522375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 50c6e1e4-15d4-41da-908a-e9e2eac6ad2a · outbound

This paper cites Bypassing backdoor detection algorithms in deep learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Bypassing backdoor detection algorithms in deep learning

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.499164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 38525825-23cb-42e0-8610-bf7c7bbd899a · outbound

This paper cites Fixmatch: Simplifying semi-supervised learning with consistency and confidence.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Fixmatch: Simplifying semi-supervised learning with consistency and confidence

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.488899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c57635da-3c4a-43ea-82fa-278124bda9c3 · outbound

This paper cites Concentration of measure and isoperi- metric inequalities in product spaces.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Concentration of measure and isoperi- metric inequalities in product spaces

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.478273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 314d3776-cd6e-4e1c-8125-97d0bba222c3 · outbound

This paper cites Defending against patch-based backdoor attacks on self- supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Defending against patch-based backdoor attacks on self- supervised learning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.466729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9ce0f2ef-2a96-4744-8f37-d615e8f1270c · outbound

This paper cites Label-Consistent Backdoor Attacks.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Label-Consistent Backdoor Attacks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T18:12:21.001980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68d5ca4e-98a7-4348-8b13-55edaec11439 · outbound

This paper cites Unlocking the power of open set: A new perspective for open-set noisy label learn- ing.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Unlocking the power of open set: A new perspective for open-set noisy label learn- ing

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.454971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f7f2be35-9bbb-4b11-91d1-0baa7d3cff80 · outbound

This paper cites Learning from complementary labels via partial-output consistency regularization.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Learning from complementary labels via partial-output consistency regularization

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.442332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 60abd80d-a965-43f8-8b4f-2ffaffb88113 · outbound

This paper cites Mm-bd: Post-training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum mar- gin statistic.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Mm-bd: Post-training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum mar- gin statistic

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.430517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 22b2ccc8-fcf0-4dbf-b8cb-aaa293d0e956 · outbound

This paper cites Mm-bd: Post-training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum mar- gin statistic.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Mm-bd: Post-training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum mar- gin statistic

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.418907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2ae329f9-b45c-40a9-a47f-36041216a137 · outbound

This paper cites An invisible black-box backdoor at- tack through frequency domain.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning An invisible black-box backdoor at- tack through frequency domain

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.406538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d9b994e9-189b-4e71-b1db-5ec9990bfad8 · outbound

This paper cites Usb: A unified semi-supervised learning bench- mark for classification.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Usb: A unified semi-supervised learning bench- mark for classification

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.393222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5c567393-9958-46e4-b1e1-674b763f1ca6 · outbound

This paper cites Freematch: Self-adaptive thresholding for semi-supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Freematch: Self-adaptive thresholding for semi-supervised learning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.382606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b2501ea7-8e4a-4c81-a89b-f6389a11b7c6 · outbound

This paper cites Unsupervised data augmentation for consistency training.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Unsupervised data augmentation for consistency training

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.371394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 511417f4-3571-4b82-95eb-f2d0bfba194d · outbound

This paper cites Generative- discriminative complementary learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Generative- discriminative complementary learning

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.358096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b11a9235-cdb6-49eb-a25c-bcd0696085ef · outbound

This paper cites Dash: Semi-supervised learning with dynamic thresholding.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Dash: Semi-supervised learning with dynamic thresholding

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.345859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 49f02e25-6373-42a2-baef-6112abac0adc · outbound

This paper cites Dehib: Deep hidden backdoor attack on semi-supervised learning via adversarial perturbation.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Dehib: Deep hidden backdoor attack on semi-supervised learning via adversarial perturbation

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.334429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 56a2f69c-e055-4036-97f5-ad77d68b125c · outbound

This paper cites Deep neural backdoor in semi-supervised learning: Threats and countermeasures.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Deep neural backdoor in semi-supervised learning: Threats and countermeasures

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.321362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c3f7bfe1-725d-4966-a48c-eb43e2b68622 · outbound

This paper cites Learning with biased complementary labels.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Learning with biased complementary labels

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.309499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 54bc8fc4-ff58-4f54-bb24-b0459b672329 · outbound

This paper cites Rethink- ing the backdoor attacks’ triggers: A frequency perspective.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Rethink- ing the backdoor attacks’ triggers: A frequency perspective

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.297046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 10ffab7e-f5f5-4504-975c-be63bcbe26b7 · outbound

This paper cites S4l: Self-supervised semi-supervised learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning S4l: Self-supervised semi-supervised learning

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.176681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 437cb077-2cd4-4eaf-aefd-ba8cb1489526 · outbound

This paper cites Flexmatch: Boosting semi-supervised learning with curricu- lum pseudo labeling.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Flexmatch: Boosting semi-supervised learning with curricu- lum pseudo labeling

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.165622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 10f2e22d-3bd5-4fe5-bf30-0444de26b4f9 · outbound

This paper cites mixup: Beyond empirical risk minimiza- tion.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning mixup: Beyond empirical risk minimiza- tion

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T18:12:21.154001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 469c6385-111d-4d39-84b4-4b90fa0af656 · outbound

This paper cites Backdoor defense via deconfounded representation learning.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Backdoor defense via deconfounded representation learning

Reference 62

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T18:12:21.141246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bb78bbb1-9c34-4ade-9428-bc6fe5933af3 · outbound

This paper cites an unresolved cited work.

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning Unresolved cited work

Reference 2023

Resolution: parse uncertain; raw_fallback, observed 2026-08-08T18:12:21.509600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers