SoK: Colluding Adversaries in Machine Learning Pipelines | Paper Citation Record

Observation f09afa7e-b046-40ec-8094-9d2b2649b2f3 · outbound

This paper cites On the alignment of group fairness with attribute privacy.

SoK: Colluding Adversaries in Machine Learning Pipelines On the alignment of group fairness with attribute privacy

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0db3a41-5f72-49b5-8eee-313eaa77802b · outbound

This paper cites SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification.

SoK: Colluding Adversaries in Machine Learning Pipelines SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.539735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 403014c9-b9b9-47b7-a38c-6620ed20f3eb · outbound

This paper cites Measuring Non-Adversarial Reproduction of Training Data in Large Language Models.

SoK: Colluding Adversaries in Machine Learning Pipelines Measuring Non-Adversarial Reproduction of Training Data in Large Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.492459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f78a0653-0662-4bf7-bf13-8a93dabf9239 · outbound

This paper cites Square attack: a query-efficient black-box adversarial attack via ran- dom search.

SoK: Colluding Adversaries in Machine Learning Pipelines Square attack: a query-efficient black-box adversarial attack via ran- dom search

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff37f54e-8506-4a26-a206-d48799ef54e4 · outbound

This paper cites Static vs.

SoK: Colluding Adversaries in Machine Learning Pipelines Static vs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9107eeff-f4a9-4aa4-89d0-95277d2d0a4c · outbound

This paper cites Blind backdoors in deep learning models.

SoK: Colluding Adversaries in Machine Learning Pipelines Blind backdoors in deep learning models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 838d4fd6-6acb-44cc-bc4d-2fa5c545b9bd · outbound

This paper cites CSI NN: Reverse engineering of neu- ral network architectures through electromagnetic side channel.

SoK: Colluding Adversaries in Machine Learning Pipelines CSI NN: Reverse engineering of neu- ral network architectures through electromagnetic side channel

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddf274b8-a1ea-460c-9e38-31996f25a46a · outbound

This paper cites Chosen ciphertext attacks against protocols based on the rsa encryption standard pkcs #1.

SoK: Colluding Adversaries in Machine Learning Pipelines Chosen ciphertext attacks against protocols based on the rsa encryption standard pkcs #1

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60c05df6-4978-4eeb-aa5c-e4e543de26b9 · outbound

This paper cites Sok: Gradient inversion attacks in federated learning.

SoK: Colluding Adversaries in Machine Learning Pipelines Sok: Gradient inversion attacks in federated learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 739b77c6-4cf8-43c6-9f45-2b1566c40ee4 · outbound

This paper cites Extracting training data from large language models.

SoK: Colluding Adversaries in Machine Learning Pipelines Extracting training data from large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c65b88c3-ad14-48cf-af78-c7590a69981c · outbound

This paper cites Membership inference attacks from first principles.

SoK: Colluding Adversaries in Machine Learning Pipelines Membership inference attacks from first principles

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb68bef1-7ad3-4117-b141-9b71abc8b8e2 · outbound

This paper cites The privacy onion effect: Mem- orization is relative.

SoK: Colluding Adversaries in Machine Learning Pipelines The privacy onion effect: Mem- orization is relative

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fd7fcf6-19c0-4ee9-be60-82a01a2550f0 · outbound

This paper cites Extracting training data from diffusion models.

SoK: Colluding Adversaries in Machine Learning Pipelines Extracting training data from diffusion models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94efd86d-ba91-4802-af11-79be1c394e34 · outbound

This paper cites Stealing Part of a Production Language Model.

SoK: Colluding Adversaries in Machine Learning Pipelines Stealing Part of a Production Language Model

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.530859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 37e2700e-8509-45b7-9198-f2d6abdd943f · outbound

This paper cites Property inference from poisoning.

SoK: Colluding Adversaries in Machine Learning Pipelines Property inference from poisoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7503234e-c98e-42aa-a60b-7f6f5d7881cf · outbound

This paper cites Snap: Efficient extraction of private properties with poisoning.

SoK: Colluding Adversaries in Machine Learning Pipelines Snap: Efficient extraction of private properties with poisoning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a9832ca-fc34-45f7-b230-2a474b399ed4 · outbound

This paper cites Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs.

SoK: Colluding Adversaries in Machine Learning Pipelines Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.504781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9b49b6b0-3ae8-4d06-beef-aaf45630adb4 · outbound

This paper cites Privacy and fairness in federated learning: On the perspective of tradeoff.ACM Comput.

SoK: Colluding Adversaries in Machine Learning Pipelines Privacy and fairness in federated learning: On the perspective of tradeoff.ACM Comput

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3d6806d-519a-4925-8167-6e3741168953 · outbound

This paper cites Amplifying membership exposure via data poisoning.

SoK: Colluding Adversaries in Machine Learning Pipelines Amplifying membership exposure via data poisoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04cbff13-ee89-4eb0-805f-4a713e495b0d · outbound

This paper cites A method to fa- cilitate membership inference attacks in deep learning models.

SoK: Colluding Adversaries in Machine Learning Pipelines A method to fa- cilitate membership inference attacks in deep learning models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2175e52-7763-4aac-9063-52ad8657715d · outbound

This paper cites Long-tailed adversarial training with self-distillation.

SoK: Colluding Adversaries in Machine Learning Pipelines Long-tailed adversarial training with self-distillation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d18c4694-cca8-40d2-bc5c-4e1c0f901011 · outbound

This paper cites Choquette-Choo et al.

SoK: Colluding Adversaries in Machine Learning Pipelines Choquette-Choo et al

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf5c5184-92d6-4fb1-bb3a-9e067e65af65 · outbound

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

SoK: Colluding Adversaries in Machine Learning Pipelines Wild patterns reloaded: A survey of machine learning security against training data poisoning.ACM Comput

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acef0602-157c-4dba-9bff-e36f72770b2a · outbound

This paper cites Energy-latency at- tacks via sponge poisoning.Information Sciences, 702:121905, 2025.

SoK: Colluding Adversaries in Machine Learning Pipelines Energy-latency at- tacks via sponge poisoning.Information Sciences, 702:121905, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e298ed31-75ff-415e-8fa0-6402366228ff · outbound

This paper cites Why do adversarial attacks transfer? explaining transferability of evasion and poi- soning attacks.

SoK: Colluding Adversaries in Machine Learning Pipelines Why do adversarial attacks transfer? explaining transferability of evasion and poi- soning attacks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c855dc1-de8a-4306-8403-e2404462d165 · outbound

This paper cites Vertexserum: Poisoning graph neural networks for link inference.

SoK: Colluding Adversaries in Machine Learning Pipelines Vertexserum: Poisoning graph neural networks for link inference

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46700f41-feb6-4aa0-be20-7e4adcc130a8 · outbound

This paper cites Are diffusion models vulnerable to membership inference attacks? InICML, 2023.

SoK: Colluding Adversaries in Machine Learning Pipelines Are diffusion models vulnerable to membership inference attacks? InICML, 2023

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5351836b-be6c-4941-b63c-49fa8feb61d2 · outbound

This paper cites Do Membership Inference Attacks Work on Large Language Models?.

SoK: Colluding Adversaries in Machine Learning Pipelines Do Membership Inference Attacks Work on Large Language Models?

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.483376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 440dbb3c-ecbc-4d40-9647-89e2f2b46b92 · outbound

This paper cites Sok: Unintended interactions among machine learning defenses and risks.

SoK: Colluding Adversaries in Machine Learning Pipelines Sok: Unintended interactions among machine learning defenses and risks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad7dbdb0-dda7-4960-8278-840b47eec15f · outbound

This paper cites Combining machine learning defenses without conflicts.

SoK: Colluding Adversaries in Machine Learning Pipelines Combining machine learning defenses without conflicts

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00e11ec3-ee6b-4261-8c5b-6d9bb295edcf · outbound

This paper cites Gifd: A generative gradient inversion method with feature domain optimization.

SoK: Colluding Adversaries in Machine Learning Pipelines Gifd: A generative gradient inversion method with feature domain optimization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dc27070-6650-4d75-84d6-6651e436afb3 · outbound

This paper cites SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge.

SoK: Colluding Adversaries in Machine Learning Pipelines SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.528004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cfe4c0ce-d005-461e-bec8-cbe292a86a75 · outbound

This paper cites Stateful defenses for machine learning models are not yet secure against black-box attacks.

SoK: Colluding Adversaries in Machine Learning Pipelines Stateful defenses for machine learning models are not yet secure against black-box attacks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a702ea-9744-4548-baf8-d0b6900e6606 · outbound

This paper cites Privacy backdoors: Stealing data with corrupted pretrained models.

SoK: Colluding Adversaries in Machine Learning Pipelines Privacy backdoors: Stealing data with corrupted pretrained models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fc98e72-f46a-4408-95ce-ac3d9d192f9d · outbound

This paper cites SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning.

SoK: Colluding Adversaries in Machine Learning Pipelines SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T02:07:33.533423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e3c8a585-c7d5-4543-92b1-8f8e6422b303 · outbound

This paper cites Differential privacy and fairness in decisions and learning tasks: A survey.

SoK: Colluding Adversaries in Machine Learning Pipelines Differential privacy and fairness in decisions and learning tasks: A survey

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ffa44d6-603a-481c-8daa-d6f1761b88d6 · outbound

This paper cites Adversarial examples make strong poisons.

SoK: Colluding Adversaries in Machine Learning Pipelines Adversarial examples make strong poisons

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80c76ff3-e26f-4a11-aa68-8d741a023142 · outbound

This paper cites \textsc{Perseus}: Tracing the Masterminds Behind Cryptocurrency Pump-and-Dump Schemes.

SoK: Colluding Adversaries in Machine Learning Pipelines \textsc{Perseus}: Tracing the Masterminds Behind Cryptocurrency Pump-and-Dump Schemes

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.536434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 32e42f91-17a7-43ca-80f1-797edfe5db2a · outbound

This paper cites Un-fair trojan: Targeted backdoor attacks against model fairness.

SoK: Colluding Adversaries in Machine Learning Pipelines Un-fair trojan: Targeted backdoor attacks against model fairness

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6174c5d9-9fc0-49db-b117-3acbd9c2ea0d · outbound

This paper cites Bias and fairness in large language models: A survey.Computational Linguistics, pages 1–79, 2024.

SoK: Colluding Adversaries in Machine Learning Pipelines Bias and fairness in large language models: A survey.Computational Linguistics, pages 1–79, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7696123-16d4-4fb7-b2a9-026f498d9dd4 · outbound

This paper cites Inverting gradients - how easy is it to break privacy in federated learning? InAdvances in Neural Information Processing Systems, pages 16937– 16947, 2020.

SoK: Colluding Adversaries in Machine Learning Pipelines Inverting gradients - how easy is it to break privacy in federated learning? InAdvances in Neural Information Processing Systems, pages 16937– 16947, 2020

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6e78812-2c76-4664-b0b6-6f8db1688647 · outbound

This paper cites An adversarial perspective on ac- curacy, robustness, fairness, and privacy: Multilateral- tradeoffs in trustworthy ml.IEEE Access, 10:120850– 120865, 2022.

SoK: Colluding Adversaries in Machine Learning Pipelines An adversarial perspective on ac- curacy, robustness, fairness, and privacy: Multilateral- tradeoffs in trustworthy ml.IEEE Access, 10:120850– 120865, 2022

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56b52f6a-ce7d-490c-a9a4-d7b2b1abffc4 · outbound

This paper cites Inversenet: Augmenting model ex- traction attacks with training data inversion.

SoK: Colluding Adversaries in Machine Learning Pipelines Inversenet: Augmenting model ex- traction attacks with training data inversion

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0476a148-4da0-42e5-b71f-71054c6e3876 · outbound

This paper cites Adversarial initialization - when your network performs the way i want -.ArXiv e-prints, February 2019.

SoK: Colluding Adversaries in Machine Learning Pipelines Adversarial initialization - when your network performs the way i want -.ArXiv e-prints, February 2019

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05c79a5c-0cdf-4bba-9c9f-35d26993334e · outbound

This paper cites On the security relevance of initial weights in deep neural networks.

SoK: Colluding Adversaries in Machine Learning Pipelines On the security relevance of initial weights in deep neural networks

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b53e37b0-8b9e-4e9a-b437-492cc0c4c7cb · outbound

This paper cites A survey on transferability of adver- sarial examples across deep neural networks.Transac- tions on Machine Learning Research (TMLR), 2024.

SoK: Colluding Adversaries in Machine Learning Pipelines A survey on transferability of adver- sarial examples across deep neural networks.Transac- tions on Machine Learning Research (TMLR), 2024

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 398bf5f1-b7e6-457f-91c8-484b36b429c5 · outbound

This paper cites What is an initial access broker (iab)? Ac- cessed 2026-05-18.

SoK: Colluding Adversaries in Machine Learning Pipelines What is an initial access broker (iab)? Ac- cessed 2026-05-18

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dbea928-682d-4036-b19f-9bed4685ce8a · outbound

This paper cites Reverse engineering convolu- tional neural networks through side-channel informa- tion leaks.

SoK: Colluding Adversaries in Machine Learning Pipelines Reverse engineering convolu- tional neural networks through side-channel informa- tion leaks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da5d8684-ff5b-4b95-9701-02a77fd23f0f · outbound

This paper cites Are attribute inference attacks just imputation? InCCS, pages 1569– 1582, 2022.

SoK: Colluding Adversaries in Machine Learning Pipelines Are attribute inference attacks just imputation? InCCS, pages 1569– 1582, 2022

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe4d982d-471a-4e92-98b9-b2eac3c96e14 · outbound

This paper cites Adversarial robustness poisoning: Increasing adversarial vulnerability of the model via data poisoning.

SoK: Colluding Adversaries in Machine Learning Pipelines Adversarial robustness poisoning: Increasing adversarial vulnerability of the model via data poisoning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9e732cf-4dec-4b99-bd8a-0fe0219e4e38 · outbound

This paper cites TOGA: Trigger optimization for clean data ordering backdoor attack, 2026.

SoK: Colluding Adversaries in Machine Learning Pipelines TOGA: Trigger optimization for clean data ordering backdoor attack, 2026

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 595a025a-9d97-473f-9a37-88edf5113186 · outbound

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

SoK: Colluding Adversaries in Machine Learning Pipelines Prada: protecting against dnn model stealing attacks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c9344ef-83ad-4960-9a04-2ea0c79c55b2 · outbound

This paper cites Thieves of sesame street: Model extraction on bert-based apis.

SoK: Colluding Adversaries in Machine Learning Pipelines Thieves of sesame street: Model extraction on bert-based apis

Reference 53

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 792d4dbc-14a4-4e26-b3db-64053fdd4662 · outbound

This paper cites Architectural backdoors for within-batch data stealing and model inference manipulation.

SoK: Colluding Adversaries in Machine Learning Pipelines Architectural backdoors for within-batch data stealing and model inference manipulation

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.507383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 4a0a7d95-84bb-4130-ae8b-e5bbbda94eb5 · outbound

This paper cites Architectural Neural Backdoors from First Principles.

SoK: Colluding Adversaries in Machine Learning Pipelines Architectural Neural Backdoors from First Principles

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01b82c9e-ee9e-4c60-9198-cc8a6a6d443e · outbound

This paper cites Enhanced label-only membership infer- ence attacks with fewer queries.

SoK: Colluding Adversaries in Machine Learning Pipelines Enhanced label-only membership infer- ence attacks with fewer queries

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ce2d6a3-8b0d-4d69-a92a-a90519ea5b52 · outbound

This paper cites Backdoor learning: A survey.IEEE Transactions on Neural Networks and Learning Sys- tems, 35:5–22, 2022.

SoK: Colluding Adversaries in Machine Learning Pipelines Backdoor learning: A survey.IEEE Transactions on Neural Networks and Learning Sys- tems, 35:5–22, 2022

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd947e40-a1ac-42ee-8a47-a1485a78762e · outbound

This paper cites From head to tail: Efficient black-box model inversion attack via long-tailed learning.

SoK: Colluding Adversaries in Machine Learning Pipelines From head to tail: Efficient black-box model inversion attack via long-tailed learning

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e5fde8f-eb73-47d0-86d6-5a4c951c1026 · outbound

This paper cites {ML-Doctor}: Holistic risk assess- ment of inference attacks against machine learning models.

SoK: Colluding Adversaries in Machine Learning Pipelines {ML-Doctor}: Holistic risk assess- ment of inference attacks against machine learning models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 368abc4b-60de-4ff8-9534-f9692ef4c05b · outbound

This paper cites Amplifying Machine Learning Attacks Through Strategic Compositions.

SoK: Colluding Adversaries in Machine Learning Pipelines Amplifying Machine Learning Attacks Through Strategic Compositions

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.515930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c2910a79-971b-446c-bfa7-62dd35466045 · outbound

This paper cites Stable bias: Evaluating societal representations in diffusion models.

SoK: Colluding Adversaries in Machine Learning Pipelines Stable bias: Evaluating societal representations in diffusion models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78f4500a-696f-4dd1-a113-fadbf39d2356 · outbound

This paper cites Analyzing leakage of personally identifiable information in language models.

SoK: Colluding Adversaries in Machine Learning Pipelines Analyzing leakage of personally identifiable information in language models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eff825f2-14fb-4324-a553-1994126863ac · outbound

This paper cites Leveraging optimization for adaptive attacks on image watermarks.

SoK: Colluding Adversaries in Machine Learning Pipelines Leveraging optimization for adaptive attacks on image watermarks

Reference 63

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 170addc7-81c1-42bb-8d26-4a60262f2c2d · outbound

This paper cites Exploring privacy and fairness risks in sharing diffusion models: An adversarial perspective.

SoK: Colluding Adversaries in Machine Learning Pipelines Exploring privacy and fairness risks in sharing diffusion models: An adversarial perspective

Reference 64

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5888f2a-969c-4235-ab6d-4031dfdbba61 · outbound

This paper cites Deepstrike: Remotely-guided fault injection attacks on dnn accelerator in cloud-fpga.

SoK: Colluding Adversaries in Machine Learning Pipelines Deepstrike: Remotely-guided fault injection attacks on dnn accelerator in cloud-fpga

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb3e77e1-ffa9-4189-aa22-827037c3acff · outbound

This paper cites Honest-but-curious nets: Sensitive attributes of private inputs can be secretly coded into the classifiers’ outputs.

SoK: Colluding Adversaries in Machine Learning Pipelines Honest-but-curious nets: Sensitive attributes of private inputs can be secretly coded into the classifiers’ outputs

Reference 66

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f56ec576-769b-4b0f-9f75-8a8c2195ff06 · outbound

This paper cites Eab-fl: Exacerbat- ing algorithmic bias through model poisoning attacks in federated learning.

SoK: Colluding Adversaries in Machine Learning Pipelines Eab-fl: Exacerbat- ing algorithmic bias through model poisoning attacks in federated learning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bfdca2f-b85f-4aa0-8bf4-f396f955a4ca · outbound

This paper cites Exacerbating algorithmic bias through fairness attacks.

SoK: Colluding Adversaries in Machine Learning Pipelines Exacerbating algorithmic bias through fairness attacks

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6d086ee-ba98-4d22-a56c-95c462f70d5b · outbound

This paper cites A survey on bias and fairness in machine learning.ACM Comput.

SoK: Colluding Adversaries in Machine Learning Pipelines A survey on bias and fairness in machine learning.ACM Comput

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82e2622e-3e66-4a04-b6da-2ccd5b5e7e38 · outbound

This paper cites Exploiting unintended feature leakage in collaborative learning.

SoK: Colluding Adversaries in Machine Learning Pipelines Exploiting unintended feature leakage in collaborative learning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c13b829-91c1-4de3-8368-9276701d80fb · outbound

This paper cites From defender to devil? un- intended risk interactions induced by llm defenses.

SoK: Colluding Adversaries in Machine Learning Pipelines From defender to devil? un- intended risk interactions induced by llm defenses

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.510156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 095fbd67-5052-42bb-bd2e-a5d5c70f5c98 · outbound

This paper cites Backdooring Bias ($B^2$) into Stable Diffusion Models.

SoK: Colluding Adversaries in Machine Learning Pipelines Backdooring Bias ($B^2$) into Stable Diffusion Models

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.501984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3850608b-1038-47a8-ad0e-0d7af84dcab3 · outbound

This paper cites Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning.

SoK: Colluding Adversaries in Machine Learning Pipelines Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ee7eed7-e7b9-4def-a791-613009fd2074 · outbound

This paper cites Towards reverse-engineering black-box neural networks.

SoK: Colluding Adversaries in Machine Learning Pipelines Towards reverse-engineering black-box neural networks

Reference 74

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09f729c2-8e51-48a5-b2bd-a2fbbf82ae8a · outbound

This paper cites I know what you trained last summer: A survey on stealing machine learning mod- els and defences.ACM Comput.

SoK: Colluding Adversaries in Machine Learning Pipelines I know what you trained last summer: A survey on stealing machine learning mod- els and defences.ACM Comput

Reference 75

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57cdd9b3-2878-4290-9f24-7cd9cc4e78d6 · outbound

This paper cites Knockoff nets: Stealing functionality of black-box models.

SoK: Colluding Adversaries in Machine Learning Pipelines Knockoff nets: Stealing functionality of black-box models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9fda3b4-98f3-49cd-a984-6104cd637c12 · outbound

This paper cites Teach llms to phish: Stealing private information from language models.

SoK: Colluding Adversaries in Machine Learning Pipelines Teach llms to phish: Stealing private information from language models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dc5f73c-c803-4913-a4f2-030ef0061f13 · outbound

This paper cites A tale of evil twins: Adversarial inputs versus poisoned models.

SoK: Colluding Adversaries in Machine Learning Pipelines A tale of evil twins: Adversarial inputs versus poisoned models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea1c2aee-3812-4b39-ad25-10db6d822695 · outbound

This paper cites Practical black-box attacks against machine learning.

SoK: Colluding Adversaries in Machine Learning Pipelines Practical black-box attacks against machine learning

Reference 79

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d41d056-13cc-4e10-8810-db6d31275ff4 · outbound

This paper cites SoK: Security and privacy in machine learning.

SoK: Colluding Adversaries in Machine Learning Pipelines SoK: Security and privacy in machine learning

Reference 80

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e279c1d2-a791-4d52-8969-6abb6c52eb70 · outbound

This paper cites Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors.

SoK: Colluding Adversaries in Machine Learning Pipelines Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors

Reference 81

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T02:07:33.513230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation bc22d108-a81d-4d9d-a155-f8e128295b26 · outbound

This paper cites Circumventing concept erasure meth- ods for text-to-image generative models.

SoK: Colluding Adversaries in Machine Learning Pipelines Circumventing concept erasure meth- ods for text-to-image generative models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c354ca72-86ee-4abe-a092-c7fba8277a3b · outbound

This paper cites Deep-Dup: An adversar- ial weight duplication attack framework to crush deep neural network in Multi-Tenant FPGA.

SoK: Colluding Adversaries in Machine Learning Pipelines Deep-Dup: An adversar- ial weight duplication attack framework to crush deep neural network in Multi-Tenant FPGA

Reference 83

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca779a1d-3a1e-43e0-bd06-f3f255a4e0c8 · outbound

This paper cites A survey of pri- vacy attacks in machine learning.ACM Comput.

SoK: Colluding Adversaries in Machine Learning Pipelines A survey of pri- vacy attacks in machine learning.ACM Comput

Reference 84

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90e99ce6-b783-4d78-8e18-be6496ad0516 · outbound

This paper cites Ml-leaks: Model and data inde- pendent membership inference attacks and defenses on machine learning models.

SoK: Colluding Adversaries in Machine Learning Pipelines Ml-leaks: Model and data inde- pendent membership inference attacks and defenses on machine learning models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c4c10fa-3b5c-4e0c-9e9f-dbbb0299363a · outbound

This paper cites SoK: Let the privacy games begin! a unified treatment of data inference privacy in machine learning.

SoK: Colluding Adversaries in Machine Learning Pipelines SoK: Let the privacy games begin! a unified treatment of data inference privacy in machine learning

Reference 86

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f60409-13da-466f-ad12-3305d96abd3c · outbound

This paper cites Membership inference attacks against machine learning models.

SoK: Colluding Adversaries in Machine Learning Pipelines Membership inference attacks against machine learning models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4f0d94f-1306-4ffb-89f6-e6f67a6fc13d · outbound

This paper cites Manipulating sgd with data order- ing attacks.

SoK: Colluding Adversaries in Machine Learning Pipelines Manipulating sgd with data order- ing attacks

Reference 88

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e2ef682-9e1b-4db0-ba08-d1c0341d0757 · outbound

This paper cites Sponge examples: Energy-latency attacks on neural networks.

SoK: Colluding Adversaries in Machine Learning Pipelines Sponge examples: Energy-latency attacks on neural networks

Reference 89

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27942447-5050-478f-bfa1-54cc29e322f8 · outbound

This paper cites Poisoning attacks on algorithmic fairness.

SoK: Colluding Adversaries in Machine Learning Pipelines Poisoning attacks on algorithmic fairness

Reference 90

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bcaae46-72dc-49c0-b260-2ee215a93f9f · outbound

This paper cites Machine learning models that remember too much.

SoK: Colluding Adversaries in Machine Learning Pipelines Machine learning models that remember too much

Reference 91

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3fa7c80-b749-496e-9a5c-84148b8b19bc · outbound

This paper cites Towards backdoor attacks and defense in robust machine learning models.Com- puters & Security, 127:103101, 2023.

SoK: Colluding Adversaries in Machine Learning Pipelines Towards backdoor attacks and defense in robust machine learning models.Com- puters & Security, 127:103101, 2023

Reference 92

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 288bf692-6691-4ed4-adf4-2949bc9502e2 · outbound

This paper cites Strobel and R.

SoK: Colluding Adversaries in Machine Learning Pipelines Strobel and R

Reference 93

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5233ab2a-dfa2-4283-a6b2-297377abc38f · outbound

This paper cites Dissecting distribution inference.

SoK: Colluding Adversaries in Machine Learning Pipelines Dissecting distribution inference

Reference 94

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 523ca1a0-9a48-4b44-8606-711d0c776db9 · outbound

This paper cites Formalizing and estimating distribution inference risks.PETS, 2022.

SoK: Colluding Adversaries in Machine Learning Pipelines Formalizing and estimating distribution inference risks.PETS, 2022

Reference 95

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffc7291c-e5e7-4cca-9ea2-3c75c87aa26d · outbound

This paper cites SoK: Pitfalls in evaluating black-box attacks.

SoK: Colluding Adversaries in Machine Learning Pipelines SoK: Pitfalls in evaluating black-box attacks

Reference 96

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a10b2eca-899b-40de-89af-506c23a1745d · outbound

This paper cites Conflicting inter- actions among protection mechanisms for machine learning models.

SoK: Colluding Adversaries in Machine Learning Pipelines Conflicting inter- actions among protection mechanisms for machine learning models

Reference 97

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b185338-970c-40b7-a0de-b7d41c6c8d70 · outbound

This paper cites Manipulating Transfer Learning for Property Inference.

SoK: Colluding Adversaries in Machine Learning Pipelines Manipulating Transfer Learning for Property Inference

Reference 98

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 900f3ccd-d75e-4475-bec2-51653f90e8cf · outbound

This paper cites Stealing machine learning models via prediction apis.

SoK: Colluding Adversaries in Machine Learning Pipelines Stealing machine learning models via prediction apis

Reference 99

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b5108b1-4270-4160-97fe-f04d80e70e9b · outbound

This paper cites On adaptive attacks to adversar- ial example defenses.

SoK: Colluding Adversaries in Machine Learning Pipelines On adaptive attacks to adversar- ial example defenses

Reference 100

Resolution: unresolved; no resolver link, observed 2026-06-27T16:10:51.471822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers