Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss | Paper Citation Record

Observation 5d80db05-dfb8-414b-907e-210012acf758 · outbound

This paper cites Improving aircraft performance using machine learning: A review.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Improving aircraft performance using machine learning: A review

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:54.398662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4dcdd1fa-0fae-48f5-a4dd-601bb7dee104 · outbound

This paper cites Deep convolutional neural network based medical image classification for disease diagnosis.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Deep convolutional neural network based medical image classification for disease diagnosis

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:54.213419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5e4f04fb-a09e-47d2-ad36-2c37db17d6fd · outbound

This paper cites Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:54.044076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1b8d5cb1-5bac-440e-ae69-3ea035d17cd8 · outbound

This paper cites Using chatgpt for human–computer interaction research: a primer.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Using chatgpt for human–computer interaction research: a primer

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:53.870003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 722906b1-ec51-489d-8375-c9f99a1c236e · outbound

This paper cites Intriguing properties of neural networks.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Intriguing properties of neural networks

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:53.705165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 48da58a4-5f0e-470c-92c0-40a230bd17e6 · outbound

This paper cites Explaining and harnessing adversarial examples.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Explaining and harnessing adversarial examples

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:53.542715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 91dcfda9-4baa-47b1-9de5-3c61ae031906 · outbound

This paper cites At- tacking vision-based perception in end-to-end autonomous driving models.Journal of Systems Architecture, 110:101766, 2020.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss At- tacking vision-based perception in end-to-end autonomous driving models.Journal of Systems Architecture, 110:101766, 2020

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:53.355397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 151febcd-87ff-46d6-b8e5-d4f4cd158e95 · outbound

This paper cites Deepfool: a simple and accurate method to fool deep neural networks.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Deepfool: a simple and accurate method to fool deep neural networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.170736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fb80231-be01-4192-90dd-86dccbcf0323 · outbound

This paper cites Carlini and D.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Carlini and D

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:53.165149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 474bd65f-8781-4368-b7db-a0011ea3fa23 · outbound

This paper cites To- wards deep learning models resistant to adversarial attacks.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss To- wards deep learning models resistant to adversarial attacks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.177491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08d70980-a39e-48ea-ba14-a2a9889ef757 · outbound

This paper cites an unresolved cited work.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T11:49:53.008923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cac32e72-30f4-4319-949d-7e33c21dbf63 · outbound

This paper cites Generating adversarial examples with adversarial networks.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Generating adversarial examples with adversarial networks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.185003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 626eab16-c1ba-4ccb-b0fb-b6cf11d238f3 · outbound

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

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.188399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f097be9-5b9c-4d92-ae5b-1ccb534bdce6 · outbound

This paper cites Adversarial training for free! In Advances in Neural Information Processing Systems, volume 32, pages 3358–3369, 2019.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Adversarial training for free! In Advances in Neural Information Processing Systems, volume 32, pages 3358–3369, 2019

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.191875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6635424-dba7-40e8-8b49-6ef1bdc7a35f · outbound

This paper cites Are labels required for improving adversarial robustness? In Advances in Neural Information Processing Systems, volume 32, 2019.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Are labels required for improving adversarial robustness? In Advances in Neural Information Processing Systems, volume 32, 2019

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.195536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315ccb4c-c826-4d32-a9b5-17c021002517 · outbound

This paper cites Theoreti- cally principled trade-off between robustness and accuracy.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Theoreti- cally principled trade-off between robustness and accuracy

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.199112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 104ab4d7-5870-4e17-8b25-09719b11e95e · outbound

This paper cites Boosting adversarial training with hypersphere embedding.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Boosting adversarial training with hypersphere embedding

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.203117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12e9dfaf-b9a3-4527-9611-10e145805ab3 · outbound

This paper cites Improving adver- sarial robustness requires revisiting misclassified examples.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Improving adver- sarial robustness requires revisiting misclassified examples

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.206830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5550bb60-c3a3-4d56-89a4-6ef93b69b2b1 · outbound

This paper cites Adversarial weight perturbation helps robust generalization.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Adversarial weight perturbation helps robust generalization

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:52.852603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 99d827b7-f279-4dd3-8319-c6abe7b1de41 · outbound

This paper cites Do Wider Neural Networks Really Help Adversarial Robustness?.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Do Wider Neural Networks Really Help Adversarial Robustness?

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.214645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1b6456e-4c0c-463e-9691-95e175c64d0c · outbound

This paper cites Lafeat: Piercing through adversarial defenses with latent features.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Lafeat: Piercing through adversarial defenses with latent features

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:52.688843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e2af0604-c67b-4cf8-a684-a4bc2f578f72 · outbound

This paper cites Mora: Improving ensemble robustness evaluation with model reweighing attack.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Mora: Improving ensemble robustness evaluation with model reweighing attack

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:52.495492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c9c6fb2e-71c5-42d2-9ba2-3d2cb363ef6c · outbound

This paper cites Lafit: Efficient and reliable evaluation of adversarial defenses with latent features.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Lafit: Efficient and reliable evaluation of adversarial defenses with latent features

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:52.339835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ac03b2ad-c8d5-41ce-9ad0-dd307814c353 · outbound

This paper cites Composite adversarial attacks.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Composite adversarial attacks

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:52.174723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9f963818-63ec-4f33-bfa4-7ad231fc0995 · outbound

This paper cites Gradient Masking Causes CLEVER to Overestimate Adversarial Perturbation Size.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Gradient Masking Causes CLEVER to Overestimate Adversarial Perturbation Size

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:49:51.451998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 095eaf16-9be1-45ec-a2ed-1f8a7e2d5bbc · outbound

This paper cites Improving Adversarial Robustness of Ensembles with Diversity Training.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Improving Adversarial Robustness of Ensembles with Diversity Training

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.235837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f872289-8c87-455b-ba9b-e6a9e69e513b · outbound

This paper cites Improving adversarial robustness via promoting ensemble diversity.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Improving adversarial robustness via promoting ensemble diversity

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:52.024010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c249167e-4ffa-4e38-a6ff-27974539afbe · outbound

This paper cites DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:49:51.425362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation da3fd4c9-b731-49ae-b30e-bfbbe2cb24e8 · outbound

This paper cites Efficient loss function by minimizing the detrimental effect of floating- point errors on gradient-based attacks.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Efficient loss function by minimizing the detrimental effect of floating- point errors on gradient-based attacks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.839593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b06c080c-27a7-4164-8507-19b5e5b4ddae · outbound

This paper cites Adversarial examples in the physical world.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Adversarial examples in the physical world

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.250788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7afa5c31-6b49-412c-988c-79144bed7d36 · outbound

This paper cites Minimally distorted adversarial examples with a fast adaptive boundary attack.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Minimally distorted adversarial examples with a fast adaptive boundary attack

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.740190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e9d99d1f-b458-4b7d-b33a-e95ced4c0e56 · outbound

This paper cites Gradient-based learning applied to document recognition.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Gradient-based learning applied to document recognition

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.258088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1875bc4b-b98a-409f-bf1a-64b0a7d1f87f · outbound

This paper cites Convolutional deep belief networks on cifar-10.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Convolutional deep belief networks on cifar-10

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.710484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9eb22942-b5af-43d3-b5a6-0ebc5a82022b · outbound

This paper cites RobustBench: a standardized adversarial robustness benchmark.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss RobustBench: a standardized adversarial robustness benchmark

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.264520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 853fdcdd-48d8-4bd1-9aa3-96015b1c175d · outbound

This paper cites Guided adversarial attack for evaluating and enhancing adversarial defenses.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Guided adversarial attack for evaluating and enhancing adversarial defenses

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.684757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 86dce101-684d-4eb0-9046-bba4fdcfe668 · outbound

This paper cites Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T11:49:51.271651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5b5ed3-ad98-49f9-b166-581f35dcfa0f · outbound

This paper cites Mma training: Direct input space margin maximization through adversarial training.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Mma training: Direct input space margin maximization through adversarial training

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.660571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1fa4e9d4-738d-485f-a82b-bd97bdf03b55 · outbound

This paper cites Zico Kolter.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Zico Kolter

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.640855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b69a0bf8-4207-403c-8275-f225b984cb8d · outbound

This paper cites Data augmentation can improve robustness.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Data augmentation can improve robustness

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.615589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 034c968e-a32d-4232-af92-f2aec11daddc · outbound

This paper cites Do wider neural networks really help adversarial robustness? In Thirty-Fifth Conference on Neural Information Processing Systems, 2021.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Do wider neural networks really help adversarial robustness? In Thirty-Fifth Conference on Neural Information Processing Systems, 2021

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.595519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c3557201-23cc-4d13-b58c-5436c889cdaa · outbound

This paper cites Unlabeled data improves adversarial robustness.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Unlabeled data improves adversarial robustness

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.580519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 47214b05-8b73-4a4a-9243-4a585e263dba · outbound

This paper cites HYDRA: Pruning Adversarially Robust Neural Networks.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss HYDRA: Pruning Adversarially Robust Neural Networks

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:49:51.377059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4e34ef2b-17d9-44c3-ba72-69e9f8a46549 · outbound

This paper cites Using pre-training can improve model robustness and uncertainty.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Using pre-training can improve model robustness and uncertainty

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.565091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d1baad83-b7ed-4329-9b09-45833aca92e2 · outbound

This paper cites Zico Kolter.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Zico Kolter

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.550229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ed5dbf5a-6c45-416c-97df-f838c1667dce · outbound

This paper cites Self-adaptive training: beyond empirical risk minimiza- tion.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Self-adaptive training: beyond empirical risk minimiza- tion

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.535024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a5dc0381-b671-4965-8582-2ead10ca39b2 · outbound

This paper cites Controlling neural level sets.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Controlling neural level sets

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.521565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aa2a8443-6fad-4db0-b7f1-73d81fd09549 · outbound

This paper cites You only propagate once: Accelerating adversarial training via maximal principle.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss You only propagate once: Accelerating adversarial training via maximal principle

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.510309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f73d54eb-ae78-4855-af25-7e65819ca216 · outbound

This paper cites SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-06T11:49:51.361513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9de5ffe7-7485-4d9e-8a26-86e9aaec85f3 · outbound

This paper cites Robustness (python library), 2019.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Robustness (python library), 2019

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.499193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 72b22890-c33c-401e-87e4-5f44610dc65f · outbound

This paper cites Do adversarially robust imagenet models transfer better? Advances in Neural Information Processing Systems, 33:3533– 3545, 2020.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Do adversarially robust imagenet models transfer better? Advances in Neural Information Processing Systems, 33:3533– 3545, 2020

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.488045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 96efe899-a3ca-4e4f-b718-49b27441f5c3 · outbound

This paper cites Decoupling direction and norm for efficient gradient-based l2 adversarial attacks and defenses.

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss Decoupling direction and norm for efficient gradient-based l2 adversarial attacks and defenses

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:49:51.476355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers