PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches | Paper Citation Record

Observation 75456b3d-2608-4152-a47f-d9e94a1399b8 · outbound

This paper cites Krishnamurthy, M.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Krishnamurthy, M

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:05.063032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c11202d1-be54-4eae-a7e8-382e2adfa44c · outbound

This paper cites Salman Asif, Srikanth V.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Salman Asif, Srikanth V

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:04.939591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 53f0326f-20e1-4948-b0c4-6b3ff2d7005d · outbound

This paper cites Asymmet- ric Loss For Multi-Label Classification.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Asymmet- ric Loss For Multi-Label Classification

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:04.849869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1ffeb14c-197a-401e-bcf9-7e4ba70b8255 · outbound

This paper cites Adversarial Patch.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Adversarial Patch

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:24:58.494232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5928bfc2-6204-443b-a0de-6688c4958445 · outbound

This paper cites Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:04.709199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ccebc7ea-6521-4bdb-bc1f-5d0288d71d92 · outbound

This paper cites Certified Defenses for Adversarial Patches.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Certified Defenses for Adversarial Patches

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:02.072575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d92e671c-713b-4f79-ace6-adf6d0d285a9 · outbound

This paper cites Cohen, Elan Rosenfeld, and J.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Cohen, Elan Rosenfeld, and J

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:04.614985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 96452744-a6a1-4bb2-a881-e47fb0f75063 · outbound

This paper cites Improved Regularization of Convolutional Neural Networks with Cutout.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Improved Regularization of Convolutional Neural Networks with Cutout

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:24:58.734603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3ae16b9-15b5-4c3c-903a-6e62f7c9752a · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:24:58.795839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1589c3d0-8a5a-430a-a741-58f5b1e2f248 · outbound

This paper cites Mul- tiClass Object Classification in Video Surveillance Systems - Experimental Study.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Mul- tiClass Object Classification in Video Surveillance Systems - Experimental Study

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:04.490681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 49e24b47-823b-49b9-be37-95ef75ed6327 · outbound

This paper cites an unresolved cited work.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:25:04.354017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 46bd6aef-3827-4b34-806b-910fbeecb41b · outbound

This paper cites Robust Physical-World Attacks on Deep Learning Visual Classification.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Robust Physical-World Attacks on Deep Learning Visual Classification

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:04.220045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2118b928-b281-40ac-8697-c160f4d6ba10 · outbound

This paper cites Recognizing Prod- ucts: A Per-exemplar Multi-label Image Classification Approach.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Recognizing Prod- ucts: A Per-exemplar Multi-label Image Classification Approach

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:04.069259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 904a617a-3f77-4a1f-a67a-5a7ebab2ac4b · outbound

This paper cites On Visible Adversarial Perturbations & Digital Watermarking.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches On Visible Adversarial Perturbations & Digital Watermarking

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:03.940328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 20962e19-3ce2-4b3f-8171-1b0d0a796588 · outbound

This paper cites MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:01.893673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 58d01bcb-ee5f-4829-9086-1b9209a62634 · outbound

This paper cites Action-Slot: Visual Action-Centric Representations for Multi- Label Atomic Activity Recognition in Traffic Scenes.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Action-Slot: Visual Action-Centric Representations for Multi- Label Atomic Activity Recognition in Traffic Scenes

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:03.835194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 56f61f24-0e4a-4ff4-883b-277ecea441e7 · outbound

This paper cites (De)Randomized Smoothing for Certifiable Defense against Patch Attacks.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches (De)Randomized Smoothing for Certifiable Defense against Patch Attacks

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:01.791349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ffc74b59-ac97-4f6c-8220-50b9b07dfdb1 · outbound

This paper cites A Survey of Convolutional Neural Networks: Analysis, Appli- cations, and Prospects.IEEE Transactions on Neural Networks and Learning Systems, 33(12):6999–7019, 2022.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches A Survey of Convolutional Neural Networks: Analysis, Appli- cations, and Prospects.IEEE Transactions on Neural Networks and Learning Systems, 33(12):6999–7019, 2022

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:03.724021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ac4f3753-3e91-48a4-9e28-aa37f37e23f6 · outbound

This paper cites Microsoft COCO: Common Objects in Context.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Microsoft COCO: Common Objects in Context

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:24:59.475107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd6c77f-86e5-433f-8c74-4ac0ad394d3e · outbound

This paper cites Query2Label: A Simple Transformer Way to Multi-Label Classification.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Query2Label: A Simple Transformer Way to Multi-Label Classification

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:24:59.536469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 697d86f6-523a-43a5-827a-666575b521da · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:24:59.626489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b62fa44-7fa6-45f2-aca9-979550b77be1 · outbound

This paper cites Semantic-Aware Multi- Label Adversarial Attacks.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Semantic-Aware Multi- Label Adversarial Attacks

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:03.615771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2fa7600f-0d31-41e3-a4ed-b1a483d1643e · outbound

This paper cites Do- main Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers.IEEE Transactions on P attern Analysis and Machine Intelligence, 44(12):9944–9959, 2022.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Do- main Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers.IEEE Transactions on P attern Analysis and Machine Intelligence, 44(12):9944–9959, 2022

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:03.509457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ef3d7911-ab4b-46f9-adc0-4e72f2d73ca2 · outbound

This paper cites Efficient Certified Defenses Against Patch Attacks on Image Classifiers.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Efficient Certified Defenses Against Patch Attacks on Image Classifiers

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:03.341491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3bd8689f-d062-4569-bbae-310f9b126e3a · outbound

This paper cites Local Gradients Smoothing: Defense against localized adversarial attacks.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Local Gradients Smoothing: Defense against localized adversarial attacks

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:25:01.509601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e9c161ba-9cb0-46c3-bcd6-573f4a49b8de · outbound

This paper cites Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:01.386907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 38266ce3-198e-4397-a35d-cc76e3ba7f03 · outbound

This paper cites Efficient Certified Defenses Against Patch Attacks on Image Classifiers.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Efficient Certified Defenses Against Patch Attacks on Image Classifiers

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:25:01.639918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 22e12986-fa89-4c73-b0a2-f9a5c0ef63c8 · outbound

This paper cites Revisiting Im- age Classifier Training for Improved Certified Robust Defense 9 against Adversarial Patches.Transactions on Machine Learning Research, 2023.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Revisiting Im- age Classifier Training for Improved Certified Robust Defense 9 against Adversarial Patches.Transactions on Machine Learning Research, 2023

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:02.979368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 91ec27a7-7b0e-4719-8fdc-ce51d77e0eca · outbound

This paper cites Certified Patch Robustness via Smoothed Vision Transformers.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Certified Patch Robustness via Smoothed Vision Transformers

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:02.852540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation aca0b6b1-403b-41f9-9440-f0ed4ce96e07 · outbound

This paper cites ML-Decoder: Scalable and V ersatile Classification Head.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches ML-Decoder: Scalable and V ersatile Classification Head

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:03.160251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2bc61404-761e-4d1c-a353-db977e2408ff · outbound

This paper cites PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:01.288504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e4f6d7c8-177d-464f-aed5-9209d7b9335f · outbound

This paper cites PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:01.162820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 806aa612-f4ff-48fc-ab36-ae0701f4ada3 · outbound

This paper cites Intriguing properties of neural networks.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Intriguing properties of neural networks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:25:00.245643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e720f58-9569-4c3f-bd71-5a23e7cf47b0 · outbound

This paper cites ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:00.997325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2419a27f-238e-41d8-946a-e28d845575e0 · outbound

This paper cites PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:00.917387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 396270a7-e4d9-490a-95f9-c46bce406e1a · outbound

This paper cites PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:01.088473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5e553a05-0803-431e-87cd-10576346f566 · outbound

This paper cites Grace Hua, Matthias Hein, and Jan Hendrik Metzen.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Grace Hua, Matthias Hein, and Jan Hendrik Metzen

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:02.733109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0a5e253d-8f75-47b2-85b5-7307e6487a7f · outbound

This paper cites A Review on Multi-Label Learning Algorithms.IEEE Transactions on Knowledge and Data Engineering, 26(8):1819–1837, 2014.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches A Review on Multi-Label Learning Algorithms.IEEE Transactions on Knowledge and Data Engineering, 26(8):1819–1837, 2014

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:02.600807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7f141f62-1501-406f-814b-6ab294e0842b · outbound

This paper cites Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:25:00.851314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation db3aed9a-3a65-40eb-b25b-a1154ec0f379 · outbound

This paper cites an unresolved cited work.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:25:02.479807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 603ccab7-f2b2-4ddb-9d20-601972ed24d9 · outbound

This paper cites disagreer.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches disagreer

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:25:02.376987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d41ab500-6c12-4f73-9927-f791c986111c · outbound

This paper cites The former works by placing two square masks at random locations on training images, with each mask covering at most25% of the image area [8, 33].

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches The former works by placing two square masks at random locations on training images, with each mask covering at most25% of the image area [8, 33]

Reference 45

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T12:25:02.252844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 058b0fe7-33ea-4ea3-bc14-5779b2e8d5cc · outbound

This paper cites Certified Adversarial Robustness via Randomized Smoothing.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Certified Adversarial Robustness via Randomized Smoothing

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T12:24:58.684323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d304ef5-2a6e-40de-a3fd-4c393b1b0fd9 · outbound

This paper cites Asymmetric Loss For Multi-Label Classification.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Asymmetric Loss For Multi-Label Classification

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T12:24:58.428977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60173037-8c4a-434a-9d37-b6359f2ab016 · outbound

This paper cites Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation.

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T12:25:00.573437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers