Paper Citation Record · LEDGER

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

As of 9 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 5 inbound Pith citation observations for arXiv:2506.02362.

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

pith.paper-citation-record.v1
2506.02362 v1

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:29:49.140988Z

measured 70 of 70 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:23:07.680268Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T01:47:04.386257Z

Reference resolution

65 of 65 outbound references displayed

verified exact1
verified fuzzy42
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 96c75794-e6be-4f5f-ab25-f440b4922437 · outbound

This paper cites Turning your weakness into a strength: Watermarking deep neural networks by backdooring.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Turning your weakness into a strength: Watermarking deep neural networks by backdooring

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.383335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation be2e1a90-1d5f-4fd9-9a63-0f39a787d654 · outbound

This paper cites Backpropagation and stochastic gradient descent method.Neurocomputing, 5(4-5):185–196, 1993.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Backpropagation and stochastic gradient descent method.Neurocomputing, 5(4-5):185–196, 1993

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.367144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4bf8f852-8f14-4a77-b99b-b19f53f8c588 · outbound

This paper cites Knowledge distillation: A good teacher is patient and consistent.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Knowledge distillation: A good teacher is patient and consistent

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:43.068897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a5c073c-aa9a-4c3e-9684-cd0e2b2b7c20 · outbound

This paper cites Data sharing and interoperability: Fostering in- novation and competition through apis.Computer Law & Security Review, 35(5):105314, 2019.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Data sharing and interoperability: Fostering in- novation and competition through apis.Computer Law & Security Review, 35(5):105314, 2019

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.341246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a3d4e200-4019-494e-8d89-8ced57857a80 · outbound

This paper cites ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:43.246771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ea5740c-d6ed-43a8-9d60-590fb24db916 · outbound

This paper cites The mnist database of handwritten digit images for machine learning research [best of the web].IEEE signal processing magazine, 29(6):141–142, 2012.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models The mnist database of handwritten digit images for machine learning research [best of the web].IEEE signal processing magazine, 29(6):141–142, 2012

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:43.346168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bde58b8-d2d0-4209-9809-52ee97f3304c · outbound

This paper cites Simon and Schuster, 2024.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Simon and Schuster, 2024

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.314420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 41cd6786-0211-476e-93c5-9e4226f9f477 · outbound

This paper cites An optimized intelligent open-source mlaas framework for user-friendly clustering and anomaly detection.The Journal of Supercomputing, 80(18):26658–26684, 2024.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models An optimized intelligent open-source mlaas framework for user-friendly clustering and anomaly detection.The Journal of Supercomputing, 80(18):26658–26684, 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.296348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fc6d3599-e8f9-4b43-985f-8551e58340d4 · outbound

This paper cites Efficient knowledge distillation from an ensemble of teachers.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Efficient knowledge distillation from an ensemble of teachers

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.280408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 08e040c4-6dc7-4d73-9c5b-57430b1014a3 · outbound

This paper cites Model extraction attacks and defenses on cloud-based machine learning models.IEEE Communications Magazine, 58(12):83–89, 2021.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Model extraction attacks and defenses on cloud-based machine learning models.IEEE Communications Magazine, 58(12):83–89, 2021

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.263164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f16855de-899f-425e-8ec3-eda7369586a2 · outbound

This paper cites Machine learning as a service (mlaas)—an enterprise perspective.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Machine learning as a service (mlaas)—an enterprise perspective

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.246872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6092f782-cd91-4955-acd6-94fdf7de893d · outbound

This paper cites A realistic model extraction attack against graph neural networks.Knowledge-Based Systems, 300:112144, 2024.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models A realistic model extraction attack against graph neural networks.Knowledge-Based Systems, 300:112144, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.230260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 191e257e-35d0-42db-89c6-516d0d3adc49 · outbound

This paper cites The content moderator’s dilemma: Removal of toxic content and distortions to online discourse.arXiv preprint arXiv:2412.16114, 2024.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models The content moderator’s dilemma: Removal of toxic content and distortions to online discourse.arXiv preprint arXiv:2412.16114, 2024

Reference 13

Resolution: verified exact; raw_fallback, observed 2026-08-07T11:29:49.617476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bea71f1e-f0d2-4ac2-ba6b-2269554dde38 · outbound

This paper cites Deep residual learning for image recognition.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Deep residual learning for image recognition

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:43.878264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 360b649d-826d-47d2-93d2-9288587b41ed · outbound

This paper cites Protecting intellectual property of language generation apis with lexical watermark.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Protecting intellectual property of language generation apis with lexical watermark

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.202338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 237dbdeb-8571-40fd-bd3b-d76d7054ec25 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Distilling the Knowledge in a Neural Network

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:44.014750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30a2ff01-83d9-4c90-a8f9-89c8f82635fd · outbound

This paper cites Learning to learn from apis: Black-box data-free meta-learning.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Learning to learn from apis: Black-box data-free meta-learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.184692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a0eb8dd1-8ebe-4440-98b0-1f1accb9c403 · outbound

This paper cites Densely connected convolutional networks.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Densely connected convolutional networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:44.142842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ee8aefd-9dfe-4e30-ada2-4bdd7f01e201 · outbound

This paper cites High accuracy and high fidelity extraction of neural networks.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models High accuracy and high fidelity extraction of neural networks

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.154429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 808ccce3-1d0b-4dc7-b312-c9530357ddec · outbound

This paper cites A comprehensive defense framework against model extraction attacks.IEEE Transactions on Dependable and Secure Computing, 21(2):685–700, 2023.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models A comprehensive defense framework against model extraction attacks.IEEE Transactions on Dependable and Secure Computing, 21(2):685–700, 2023

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.138246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 81706863-f513-4aba-a4f3-f4af169e4e8b · outbound

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

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Prada: protecting against dnn model stealing attacks

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:55.104879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1beb6478-54f6-405c-9fa9-a0152c35184b · outbound

This paper cites Maze: Data-free model stealing attack using zeroth-order gradient estimation.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Maze: Data-free model stealing attack using zeroth-order gradient estimation

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:54.977984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5f09adf9-dcb7-4d48-9041-4598d94e609c · outbound

This paper cites Protecting dnns from theft using an ensemble of diverse models.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Protecting dnns from theft using an ensemble of diverse models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:54.798480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3955441e-2fd8-43a1-90d3-71bf3e8bf34e · outbound

This paper cites Defending against model stealing attacks with adaptive misinformation.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Defending against model stealing attacks with adaptive misinformation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:44.591416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88cf8439-7dd9-4013-997b-8cee12db35d0 · outbound

This paper cites Model extraction warning in mlaas paradigm.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Model extraction warning in mlaas paradigm

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:54.641699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6618bcec-d434-4885-996c-5257588e200a · outbound

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

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models NSML: Meet the MLaaS platform with a real-world case study

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:44.746123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73a7fe6d-21f5-4f2f-a3b8-5414edb419ed · outbound

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

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Learning multiple layers of features from tiny images

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:44.852634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe4c7ba1-a2ba-4621-beaf-3968cc1f29ae · outbound

This paper cites An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier.International Journal of Cognitive Computing in Engineering, 2:40–46, 2021.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier.International Journal of Cognitive Computing in Engineering, 2:40–46, 2021

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:54.518261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f5cddcb3-116c-4e84-ba76-b0d8c9c1f670 · outbound

This paper cites Defending against model extraction attacks with physical unclonable function.Information Sciences, 628:196–207, 2023.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Defending against model extraction attacks with physical unclonable function.Information Sciences, 628:196–207, 2023

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:54.362252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d443e543-093d-48c1-ad5e-cad525dc2094 · outbound

This paper cites PhD thesis, Nanyang Technological University, 2025.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models PhD thesis, Nanyang Technological University, 2025

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:54.240412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bd4ea582-1b84-450d-a09c-38891304ff16 · outbound

This paper cites Defending against model extraction attacks with ood feature learning and decision boundary confusion.Computers & Security, 136:103563, 2024.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Defending against model extraction attacks with ood feature learning and decision boundary confusion.Computers & Security, 136:103563, 2024

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:54.115666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 43951b68-0877-4be8-875a-76f137355351 · outbound

This paper cites Model extraction attacks revisited.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Model extraction attacks revisited

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:45.383709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8baa84a2-ce0d-4bb3-b2e8-0f4f0f62093d · outbound

This paper cites Quda: Query-limited data-free model extraction.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Quda: Query-limited data-free model extraction

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:54.057746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4f23fa17-4653-46b4-b192-46ce5dd9a5b8 · outbound

This paper cites Model extraction attack and defense on deep generative models.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Model extraction attack and defense on deep generative models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:53.771059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cb1dd927-8bca-4b6d-b6dc-237b57b43496 · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:45.638448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f562e1f9-6a63-46ce-9c48-6ee40a31722e · outbound

This paper cites Dynamic neural fortresses: An adaptive shield for model extraction defense.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Dynamic neural fortresses: An adaptive shield for model extraction defense

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:53.456411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f0bec78b-5abf-4f04-b142-b25cbf44dff8 · outbound

This paper cites Dataset Inference: Ownership Resolution in Machine Learning.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Dataset Inference: Ownership Resolution in Machine Learning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:45.809923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9674f173-d260-4e28-aa78-1212ee20ce3b · outbound

This paper cites How to steer your adversary: Targeted and efficient model stealing defenses with gradient redirection.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models How to steer your adversary: Targeted and efficient model stealing defenses with gradient redirection

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:45.889360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38841a3d-9dc2-47e3-98bf-60f0746a90df · outbound

This paper cites Mixed Precision Training.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Mixed Precision Training

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:45.960731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07a5608d-af51-4df9-a12d-4e48c60259e5 · outbound

This paper cites Megex: Data-free model extraction attack against gradient-based explainable ai.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Megex: Data-free model extraction attack against gradient-based explainable ai

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:53.111340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dc245ebc-7ae6-4888-8f4f-737b6e094c16 · outbound

This paper cites The MIT Press, 2nd edition, 2018.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models The MIT Press, 2nd edition, 2018

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:52.781143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a7bd935f-e061-422c-baf9-b48e639436c0 · outbound

This paper cites PhD thesis, Technische Universität Wien, 2023.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models PhD thesis, Technische Universität Wien, 2023

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:52.694587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 022aa366-53cd-474e-bf7d-bcf7dc2eccb7 · outbound

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

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Knockoff nets: Stealing functionality of black-box models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:46.405187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65aca9c0-a9e8-4ee8-93e7-fbd27e69b3f9 · outbound

This paper cites Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:46.552480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08f13667-6af2-48e7-91f2-ac6a2f8a4025 · outbound

This paper cites Mod- elshield: Adaptive and robust watermark against model extraction attack.IEEE Transactions on Information Forensics and Security, 2025.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Mod- elshield: Adaptive and robust watermark against model extraction attack.IEEE Transactions on Information Forensics and Security, 2025

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:52.574431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ce321895-d395-4e4c-b557-f5a060d3255c · outbound

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

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Practical black-box attacks against machine learning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:46.841381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f57c3fd-0138-41fa-abc5-525e67ddcc6a · outbound

This paper cites Relational knowledge distillation.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Relational knowledge distillation

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:46.989656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b2e1da6-907e-46ba-896e-e8e6c79b96b5 · outbound

This paper cites Automatic differentiation in pytorch.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Automatic differentiation in pytorch

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:47.088565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87d3db77-060a-4b57-9b4e-8a27b012886f · outbound

This paper cites Mlaas: Machine learning as a service.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Mlaas: Machine learning as a service

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:52.399547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3d91047b-bac6-4082-b95e-6827687c079d · outbound

This paper cites Privacy as intellectual property.Stan.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Privacy as intellectual property.Stan

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:52.283298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 779fd938-78b7-4503-9b3a-c3251d6657c5 · outbound

This paper cites Mobilenetv2: Inverted residuals and linear bottlenecks.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Mobilenetv2: Inverted residuals and linear bottlenecks

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:47.448509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a09ea711-c052-4ca0-8b65-5901ecb25f93 · outbound

This paper cites Towards data-free model stealing in a hard label setting.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Towards data-free model stealing in a hard label setting

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:52.180612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 97d8357e-3a61-4bce-9494-d1e8cfce3c1b · outbound

This paper cites On efficient training of large-scale deep learning models.ACM Computing Surveys, 57(3):1–36, 2024.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models On efficient training of large-scale deep learning models.ACM Computing Surveys, 57(3):1–36, 2024

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:52.049503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b18395a2-b178-42ae-8fd0-71d2ddbe7b94 · outbound

This paper cites Does knowledge distillation really work?Advances in neural information processing systems, 34:6906–6919, 2021.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Does knowledge distillation really work?Advances in neural information processing systems, 34:6906–6919, 2021

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:51.910024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 06f032f6-7550-46ff-9bd2-eb488b2f58e1 · outbound

This paper cites Deep neural network watermarking against model extraction attack.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Deep neural network watermarking against model extraction attack

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:51.789268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2f0e70fb-0d69-4c23-b134-697abad43b61 · outbound

This paper cites Stealing machine learning models via prediction {APIs}.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Stealing machine learning models via prediction {APIs}

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:48.095902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 387f2316-fb70-4fc0-8316-a6da1a7e13cd · outbound

This paper cites Data-free model extraction.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Data-free model extraction

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:51.686598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a178aa32-a927-43d1-ab26-826f99153f87 · outbound

This paper cites Defending against data-free model extraction by distributionally robust defensive training.Advances in Neural Information Processing Systems, 36:624–637, 2023.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Defending against data-free model extraction by distributionally robust defensive training.Advances in Neural Information Processing Systems, 36:624–637, 2023

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:51.551622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 72d6f83c-071d-4f74-8ba8-dc106a336bab · outbound

This paper cites Defense against model extraction attack by bayesian active watermarking.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Defense against model extraction attack by bayesian active watermarking

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:51.438230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d288470e-414c-40f5-b4d6-14a0f1fe3c22 · outbound

This paper cites Zero-shot knowledge distillation from a decision-based black-box model.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Zero-shot knowledge distillation from a decision-based black-box model

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:51.249330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation db6c8b70-d670-4426-876a-7ddccb2326e4 · outbound

This paper cites Towards explainable model extraction attacks.International Journal of Intelligent Systems, 37(11):9936–9956, 2022.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Towards explainable model extraction attacks.International Journal of Intelligent Systems, 37(11):9936–9956, 2022

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:50.989219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 89442633-a36a-4eca-9d97-d71fc9a0d943 · outbound

This paper cites an unresolved cited work.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:29:50.736835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 19462489-82c2-446b-b2c6-93d1cfabf697 · outbound

This paper cites Mlmodelci: An automatic cloud platform for efficient mlaas.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Mlmodelci: An automatic cloud platform for efficient mlaas

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:50.456875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 261f865e-79f2-4b58-b2d9-217bf6e21583 · outbound

This paper cites Minimizing maximum model discrepancy for transferable black-box targeted attacks.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models Minimizing maximum model discrepancy for transferable black-box targeted attacks

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:50.234183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 80f696c6-adf2-4d0a-be40-44fff395ddd4 · outbound

This paper cites A survey of model extraction attacks and defenses in distributed computing environments, 2025.

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models A survey of model extraction attacks and defenses in distributed computing environments, 2025

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:49.864470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation 2915912e-4524-4069-9543-c9c1df610d22 · inbound

A Survey on Model Extraction Attacks and Defenses for Large Language Models cites this paper.

A Survey on Model Extraction Attacks and Defenses for Large Language Models MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T22:23:07.680268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca490b50-3be2-4d14-98ef-3e15920dd554 · inbound

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives cites this paper.

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T18:12:37.034350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5da6b5f7-7453-4261-b633-fd1d64dc03b0 · inbound

Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses cites this paper.

Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Reference 182

Resolution: unresolved; no resolver link, observed 2026-08-05T15:39:56.130610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beefe17b-0f1a-4e24-8930-e80ff25bc258 · inbound

LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer? cites this paper.

LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer? MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:47:04.388649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9dde8944-2c60-4c02-844d-c0fd23468225 · inbound

ADS-C: Antidistillation Sampling for Classification cites this paper.

ADS-C: Antidistillation Sampling for Classification MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T23:20:43.484131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.