A Unified Perspective on Adversarial Membership Manipulation in Vision Models | Paper Citation Record

Observation 67321479-e0fd-4317-9233-9c5345113495 · outbound

This paper cites Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:08:12.943303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b0aeb0de-2946-4d88-96c9-040507bbbf12 · outbound

This paper cites A Survey of Black-Box Adversarial Attacks on Computer Vision Models.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models A Survey of Black-Box Adversarial Attacks on Computer Vision Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:08:12.939748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 93799777-5c4b-42f4-bfb5-67f2b6b9c9e4 · outbound

This paper cites Pattern recognition.Machine learning, 128(9).

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Pattern recognition.Machine learning, 128(9)

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.905453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 87bf392b-d1c8-4d64-80c5-0061be4c63c0 · outbound

This paper cites Adversarial examples are not easily detected: Bypassing ten detection methods.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Adversarial examples are not easily detected: Bypassing ten detection methods

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.912675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3d2b519d-c918-45f1-83ad-25164ca7f1bd · outbound

This paper cites Towards evaluating the robustness of neural networks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Towards evaluating the robustness of neural networks

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.922491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7e60929b-39f4-409c-a222-9922db622a35 · outbound

This paper cites The secret sharer: Evaluating and testing unintended memorization in neural networks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models The secret sharer: Evaluating and testing unintended memorization in neural networks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.991405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ffdfef95-368a-462a-9476-280776f9b89b · outbound

This paper cites Membership inference attacks from first principles.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Membership inference attacks from first principles

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.033474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c285cab8-fcab-45d8-82e8-90c2f7098ffa · outbound

This paper cites Deepdriving: Learning affordance for direct perception in autonomous driving.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Deepdriving: Learning affordance for direct perception in autonomous driving

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.023245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d0835c7e-1260-46b8-a80f-a2c2213d3500 · outbound

This paper cites Gan- leaks: A taxonomy of membership inference attacks against generative models.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Gan- leaks: A taxonomy of membership inference attacks against generative models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.084652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ff4f4ff-e639-4d45-9060-48166d7dc225 · outbound

This paper cites When machine unlearn- ing jeopardizes privacy.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models When machine unlearn- ing jeopardizes privacy

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.095667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8aacc043-9bb7-40cf-aced-a3f3d4958645 · outbound

This paper cites Adversarial robustness: From self-supervised pre-training to fine-tuning.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Adversarial robustness: From self-supervised pre-training to fine-tuning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.946724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 907df2f8-2c6c-405a-8e21-4614625d04be · outbound

This paper cites Label-only membership infer- ence attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Label-only membership infer- ence attacks

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.059619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4b79dc43-cdcc-4edc-ad14-1c924211178f · outbound

This paper cites Reliable evaluation of adversarial robustness with an ensemble of diverse parameter- free attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Reliable evaluation of adversarial robustness with an ensemble of diverse parameter- free attacks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.274085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3e2ee9c1-336f-4aac-9641-ed7e293ad209 · outbound

This paper cites CINIC-10 is not ImageNet or CIFAR-10.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models CINIC-10 is not ImageNet or CIFAR-10

Reference 14

Resolution: malformed identifier; arxiv_id, observed 2026-05-13T20:08:12.972460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 686e8eaf-e79a-42bc-83c5-fc05785699a8 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Imagenet: A large-scale hierarchical image database

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.192516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f0746bc4-e0ac-4aa1-827c-aeafcb0609a0 · outbound

This paper cites Model inversion attacks that exploit confidence information and basic countermeasures.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Model inversion attacks that exploit confidence information and basic countermeasures

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.139531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c57a510f-332b-469c-8881-58b6e007a5b4 · outbound

This paper cites Property inference attacks on fully connected neural networks using permutation invariant representations.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Property inference attacks on fully connected neural networks using permutation invariant representations

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.377549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0c69cc20-8eee-42cc-80da-9228930deb22 · outbound

This paper cites Maximum mean discrepancy test is aware of adversarial attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Maximum mean discrepancy test is aware of adversarial attacks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.198545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 030e3a9b-5dc8-4d56-acd4-56fae9ba1541 · outbound

This paper cites Fast and reliable evaluation of adversarial robustness with minimum- margin attack.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Fast and reliable evaluation of adversarial robustness with minimum- margin attack

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.215219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 389a587e-a91c-445d-8be5-ebb768dbd6f3 · outbound

This paper cites Explaining and harnessing adversarial examples.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Explaining and harnessing adversarial examples

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.402791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ddadfe1a-775f-4feb-b00c-a8cf221fccbd · outbound

This paper cites On the (Statistical) Detection of Adversarial Examples.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models On the (Statistical) Detection of Adversarial Examples

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:08:12.947361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 70222f35-dde6-4228-aa9d-7e457ae9e851 · outbound

This paper cites Simple black-box adversarial attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Simple black-box adversarial attacks

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.269161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation facb1943-637c-42e2-a6e1-f7bfdd860112 · outbound

This paper cites Deep residual learning for image recognition.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Deep residual learning for image recognition

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.264732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6849b3be-7c75-475e-9438-6af5119bd625 · outbound

This paper cites an unresolved cited work.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-05-14T02:28:44.119216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9d0166ca-c875-4264-bea2-6016983a59b1 · outbound

This paper cites Resolving individuals contributing trace amounts of dna to highly complex mixtures using high-density snp genotyping microarrays.PLOS Genetics, 4:1–9.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Resolving individuals contributing trace amounts of dna to highly complex mixtures using high-density snp genotyping microarrays.PLOS Genetics, 4:1–9

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.182710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eef14edd-7265-489c-9e75-3090babd1b6f · outbound

This paper cites Scalable continuous-time diffusion framework for network inference and influence estimation.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Scalable continuous-time diffusion framework for network inference and influence estimation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.006785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a18b961a-e1a5-4d10-9026-045edde82b8c · outbound

This paper cites Black-box adversarial attacks with limited queries and information.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Black-box adversarial attacks with limited queries and information

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.934349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e7c11f15-0c03-4ebb-bfd8-9ae80bd58033 · outbound

This paper cites Memguard: Defending against black- box membership inference attacks via adversarial examples.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Memguard: Defending against black- box membership inference attacks via adversarial examples

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.159522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8b2255c5-8be5-4f4c-aaed-e34c236aab3f · outbound

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

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Learning multiple layers of features from tiny images

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.134342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1e26bad2-befa-49f8-806c-3204300383a4 · outbound

This paper cites Adver- sarial examples in the physical world.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Adver- sarial examples in the physical world

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.343612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b546ce5f-cf68-4352-8bb3-caafb7a1ba41 · outbound

This paper cites A simple unified framework for detecting out-of-distribution samples and adversarial attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models A simple unified framework for detecting out-of-distribution samples and adversarial attacks

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.126747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f1bc0700-f816-4ef9-a8f1-0ff54ff5ccd2 · outbound

This paper cites Stolen memories: Leverag- ing model memorization for calibrated white-box membership inference.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Stolen memories: Leverag- ing model memorization for calibrated white-box membership inference

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.111493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4aaf8169-b6b8-4749-9166-84c8e7d67808 · outbound

This paper cites Membership in- ference attacks and defenses in classification models.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Membership in- ference attacks and defenses in classification models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.221922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4fc15a7f-cf40-4476-a970-99969daf279d · outbound

This paper cites Adversarial examples detection in deep networks with convolutional filter statistics.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Adversarial examples detection in deep networks with convolutional filter statistics

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.951337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 01f6c749-9611-4a1b-8f8c-daedbf87ae77 · outbound

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

A Unified Perspective on Adversarial Membership Manipulation in Vision Models SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:08:12.953731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 589dc44c-bd06-4c94-a4c1-2385ae8bd474 · outbound

This paper cites Characterizing adversarial sub- spaces using local intrinsic dimensionality.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Characterizing adversarial sub- spaces using local intrinsic dimensionality

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.002746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bd5d754a-cf3c-4c93-9f21-95955dc5e7c2 · outbound

This paper cites Understanding adversarial at- tacks on deep learning based medical image analysis systems.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Understanding adversarial at- tacks on deep learning based medical image analysis systems

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.979627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1990947f-bfd2-4c01-bc43-b1595175d403 · outbound

This paper cites Visualizing data using t-sne.Journal of machine learning research, 9 (Nov):2579–2605.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Visualizing data using t-sne.Journal of machine learning research, 9 (Nov):2579–2605

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.299897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2d05d3bd-0862-4ff4-9cd1-009409c9cd6f · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Towards deep learning models resistant to adversarial attacks

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.256148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation babf07b3-ce7c-40ad-a574-9a964c641126 · outbound

This paper cites Exploiting unintended feature leakage in collaborative learning.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Exploiting unintended feature leakage in collaborative learning

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.286347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 00a7a55e-c3db-4ec9-a8a2-676e3788e6e3 · outbound

This paper cites On Detecting Adversarial Perturbations.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models On Detecting Adversarial Perturbations

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:08:12.950742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 796a9dbe-237c-439f-92a9-409e5249ef54 · outbound

This paper cites Deep learning for healthcare: review, opportunities and challenges.Briefings in bioinformatics, 19 (6):1236–1246.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Deep learning for healthcare: review, opportunities and challenges.Briefings in bioinformatics, 19 (6):1236–1246

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.335340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 50115edc-a5ca-4ef1-87d8-ce5196ee949a · outbound

This paper cites ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:08:12.957744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 878b4ece-e07e-456e-b8be-07045f6cc11b · outbound

This paper cites Machine learning with membership privacy using adversarial regu- larization.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Machine learning with membership privacy using adversarial regu- larization

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.070395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3562b203-a191-4a8b-bddd-b25f883ff76e · outbound

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

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Compre- hensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.046718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 69168e7b-febf-4d84-b752-6b33cee05f70 · outbound

This paper cites an unresolved cited work.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-05-14T02:28:44.362621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4e4d04d-734a-4ccb-843b-876f13d4cdf3 · outbound

This paper cites an unresolved cited work.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-05-14T02:28:44.171190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c208672a-6baa-40d2-96f6-986a387e9433 · outbound

This paper cites Deep neural networks are easily fooled: High confidence predictions for unrecognizable images.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.204311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8ec02745-0010-49f9-8e03-fbd3b081ddb7 · outbound

This paper cites DeepFense: Online Accelerated Defense Against Adversarial Deep Learning.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models DeepFense: Online Accelerated Defense Against Adversarial Deep Learning

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-07-04T22:59:50.548384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0160049a-3905-4b25-a00d-6556d3e847b7 · outbound

This paper cites White-box vs black- box: Bayes optimal strategies for membership inference.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models White-box vs black- box: Bayes optimal strategies for membership inference

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.314786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 13dded0c-9d99-4a51-9ff6-8ced4359d5ae · outbound

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

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Ml-leaks: Model and data indepen- dent membership inference attacks and defenses on machine learning models

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.388805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 43ae76de-d0f0-401a-b461-9cf1f1051018 · outbound

This paper cites Hats: Hardness- aware trajectory synthesis for gui agents.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Hats: Hardness- aware trajectory synthesis for gui agents

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.153844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1ffb1455-4d5f-45b0-8d46-1b1043ce14e8 · outbound

This paper cites Membership inference attacks against machine learning models.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Membership inference attacks against machine learning models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.973592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f24f1158-4dfb-49f1-b470-21faef7b68e7 · outbound

This paper cites Machine learning models that remember too much.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Machine learning models that remember too much

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.165808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e91cd55c-94c9-4559-ae60-23fcc6fd7546 · outbound

This paper cites Systematic evaluation of pri- vacy risks of machine learning models.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Systematic evaluation of pri- vacy risks of machine learning models

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.228632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cfba3fe4-d018-47ca-9ef3-db3d617a192c · outbound

This paper cites Introducing a new privacy testing library in tensorflow.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Introducing a new privacy testing library in tensorflow

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.407286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2a9e493a-3f21-4b5a-94c1-631405f1f5ab · outbound

This paper cites Intriguing properties of neural networks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Intriguing properties of neural networks

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.088583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f739bfd6-70cc-4ff5-8773-0b8a04e55950 · outbound

This paper cites Stealing machine learning models via prediction apis.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Stealing machine learning models via prediction apis

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.942518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f5d3f909-b8b6-4b76-950d-7ac2bb16b5bf · outbound

This paper cites The stronger the diffusion model, the easier the backdoor: Data poisoning to induce copyright breaches without adjusting finetuning pipeline.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models The stronger the diffusion model, the easier the backdoor: Data poisoning to induce copyright breaches without adjusting finetuning pipeline

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.969363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8bc308ca-dddd-4552-af2c-6b632ab8d43f · outbound

This paper cites On the convergence and robustness of adversarial training.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models On the convergence and robustness of adversarial training

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.144490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 972c079d-e5f8-4f69-a132-87b6b3b48d56 · outbound

This paper cites On the Importance of Difficulty Calibration in Membership Inference Attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models On the Importance of Difficulty Calibration in Membership Inference Attacks

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:08:12.965253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 63193b6b-c149-4b2b-b514-aac71037d812 · outbound

This paper cites Adversarial weight perturbation helps robust generalization.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Adversarial weight perturbation helps robust generalization

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.962107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0d0a8588-e251-425d-91a0-b49b7374d34e · outbound

This paper cites The human splicing code reveals new insights into the genetic determinants of disease.Science, 347(6218).

A Unified Perspective on Adversarial Membership Manipulation in Vision Models The human splicing code reveals new insights into the genetic determinants of disease.Science, 347(6218)

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.107678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5eabb051-df34-448d-83d4-91d4781596a7 · outbound

This paper cites Enhanced membership in- ference attacks against machine learning models.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Enhanced membership in- ference attacks against machine learning models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.056217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cf47ed50-e9a4-447d-97ad-9a6d38ece5c6 · outbound

This paper cites Privacy risk in machine learning: Analyzing the connection to overfitting.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Privacy risk in machine learning: Analyzing the connection to overfitting

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:43.998409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7db42e3c-d85b-4345-9468-110adf8a9d89 · outbound

This paper cites Wide residual networks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Wide residual networks

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.235008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e4d0c675-b452-4e74-9d99-5c48091674c7 · outbound

This paper cites Low-cost high-power membership inference attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Low-cost high-power membership inference attacks

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.243280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 520ad148-0880-49bf-902d-6b95c74722d7 · outbound

This paper cites Understanding deep learning (still) re- quires rethinking generalization.Communications of the ACM, 64:107–115.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Understanding deep learning (still) re- quires rethinking generalization.Communications of the ACM, 64:107–115

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.063135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f3761763-f997-493c-a376-bfbcf0607d1d · outbound

This paper cites Geometry-aware instance-reweighted adversarial training.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Geometry-aware instance-reweighted adversarial training

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.078072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 398e9658-af6e-4919-b94a-57413f8f373a · outbound

This paper cites Dual-path distillation: A unified framework to improve black- box attacks.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Dual-path distillation: A unified framework to improve black- box attacks

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.029235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 90c5e056-b868-49e4-9fe8-a6c6bbad24c9 · outbound

This paper cites Instead of taking a single step of size ϵ in the direction of the gradient sign, multiple smaller steps are taken in PGD (the result is clipped by the same ϵ).

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Instead of taking a single step of size ϵ in the direction of the gradient sign, multiple smaller steps are taken in PGD (the result is clipped by the same ϵ)

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.015083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7a7f24ef-ec85-4b1d-81aa-0e28dfad7379 · outbound

This paper cites Motivated by this, [5] replaced the CE loss with several possible choices.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Motivated by this, [5] replaced the CE loss with several possible choices

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T02:28:44.103272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fc15a005-15bd-4631-bfad-abb4ff7eac0d · outbound

This paper cites gradient-norm collapse.

A Unified Perspective on Adversarial Membership Manipulation in Vision Models gradient-norm collapse

Reference 73

Resolution: malformed identifier; raw_fallback, observed 2026-05-14T02:28:43.953729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6798d632-edd9-41ec-b579-8f0e8fca874e · outbound

This paper cites Shadow Models.ForAttack R[ 64], we train 100 reference models (OUT-Models).

A Unified Perspective on Adversarial Membership Manipulation in Vision Models Shadow Models.ForAttack R[ 64], we train 100 reference models (OUT-Models)

Reference 74

Resolution: malformed identifier; arxiv_id, observed 2026-05-13T20:08:12.968644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers