Paper Citation Record · LEDGER

Improving Certified Robustness via Adversarial Distillation

As of 19 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2606.31653.

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

pith.paper-citation-record.v1
2606.31653 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-01T06:11:33.633679Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

49 of 49 outbound references displayed

verified exact1
verified fuzzy44
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ea5cbbcc-2439-4bd9-8109-fd8e3e63a208 · outbound

This paper cites Adversarial training and provable defenses: Bridging the gap.

Improving Certified Robustness via Adversarial Distillation Adversarial training and provable defenses: Bridging the gap

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.965436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e46d43a9-2af1-4552-bd1d-abf277c14c28 · outbound

This paper cites Evasion attacks against machine learning at test time.

Improving Certified Robustness via Adversarial Distillation Evasion attacks against machine learning at test time

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.055117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 49654b21-983a-48c7-bd02-d271b0f0f45f · outbound

This paper cites an unresolved cited work.

Improving Certified Robustness via Adversarial Distillation Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-07-06T19:12:51.056894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 805275a2-c5bb-4797-b810-7b8e3c6889e2 · outbound

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

Improving Certified Robustness via Adversarial Distillation Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.050868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 17681aff-89d9-40c6-afb6-149d065cb25f · outbound

This paper cites Decoupled kullback-leibler divergence loss.

Improving Certified Robustness via Adversarial Distillation Decoupled kullback-leibler divergence loss

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.014933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4269974d-f3e0-4a7c-b447-a07d23ac9716 · outbound

This paper cites Learning better certified models from empirically-robust teachers, 2026.

Improving Certified Robustness via Adversarial Distillation Learning better certified models from empirically-robust teachers, 2026

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:45:40.529469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 222c93a6-5df9-4cb2-bf90-944efe5d71ca · outbound

This paper cites Pawan Kumar, and Robert Stanforth.

Improving Certified Robustness via Adversarial Distillation Pawan Kumar, and Robert Stanforth

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.058743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 13384826-4b3c-42dd-ad28-f9a2108785dc · outbound

This paper cites Pawan Kumar, Robert Stan- forth, and Alessio Lomuscio.

Improving Certified Robustness via Adversarial Distillation Pawan Kumar, Robert Stan- forth, and Alessio Lomuscio

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.034653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7ae73078-5b88-4b00-823e-4714bdb28ae1 · outbound

This paper cites Formal verification of piece-wise linear feed-forward neural networks.Auto- mated Technology for Verification and Analysis, 2017.

Improving Certified Robustness via Adversarial Distillation Formal verification of piece-wise linear feed-forward neural networks.Auto- mated Technology for Verification and Analysis, 2017

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.035799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f7f397a1-8b65-4698-ae23-f60bf8c77bd8 · outbound

This paper cites Complete verification via multi-neuron relaxation guided branch-and-bound.

Improving Certified Robustness via Adversarial Distillation Complete verification via multi-neuron relaxation guided branch-and-bound

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.065837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1644621c-b95c-41e5-84e6-a2b9989beaf5 · outbound

This paper cites Adversarially robust distillation.

Improving Certified Robustness via Adversarial Distillation Adversarially robust distillation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.969569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c90a58c-d210-4be8-9100-ed9e3212789c · outbound

This paper cites Goodfellow, Jonathon Shlens, and Christian Szegedy.

Improving Certified Robustness via Adversarial Distillation Goodfellow, Jonathon Shlens, and Christian Szegedy

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.061380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7583bbdf-ed30-4286-877f-5c681e702228 · outbound

This paper cites On the effectiveness of interval bound propagation for training verifiably robust models.

Improving Certified Robustness via Adversarial Distillation On the effectiveness of interval bound propagation for training verifiably robust models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.992338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 20da01fe-4d88-45d0-be48-9d605b3ee6b1 · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.

Improving Certified Robustness via Adversarial Distillation Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.990482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 919976b0-007a-4ec5-a298-f4cb58b9503c · outbound

This paper cites Distilling the knowledge in a neural network.

Improving Certified Robustness via Adversarial Distillation Distilling the knowledge in a neural network

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.043943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c9fee689-d145-4fd2-afdd-d0da9dae958c · outbound

This paper cites On the paradox of certified training.Transactions on Machine Learning Research, 2022.

Improving Certified Robustness via Adversarial Distillation On the paradox of certified training.Transactions on Machine Learning Research, 2022

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.017040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2dffc7db-d077-48e2-a53d-a9015f869aba · outbound

This paper cites Reluplex: An efficient SMT solver for verifying deep neural networks.

Improving Certified Robustness via Adversarial Distillation Reluplex: An efficient SMT solver for verifying deep neural networks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.998519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a90f809f-a325-4c88-bf62-e999bf072a51 · outbound

This paper cites Kingma and Jimmy Ba.

Improving Certified Robustness via Adversarial Distillation Kingma and Jimmy Ba

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.973417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 34b79291-dd37-485d-9c2a-252e9674daf2 · outbound

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

Improving Certified Robustness via Adversarial Distillation Learning multiple layers of features from tiny images

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.000590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 287f2bce-3d51-4163-a635-9831cc64435c · outbound

This paper cites Tiny imagenet visual recognition challenge.CS 231N, 7(7):3.

Improving Certified Robustness via Adversarial Distillation Tiny imagenet visual recognition challenge.CS 231N, 7(7):3

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.040214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9a673c5b-ab11-4021-b247-1cc395544f93 · outbound

This paper cites an unresolved cited work.

Improving Certified Robustness via Adversarial Distillation Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-07-06T19:12:51.010512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3251c365-c528-4217-88b9-7d2ebd65aa8c · outbound

This paper cites an unresolved cited work.

Improving Certified Robustness via Adversarial Distillation Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-07-06T19:12:51.048958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 238258a5-f5b5-4837-bb9d-afacf9f4a296 · outbound

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

Improving Certified Robustness via Adversarial Distillation Towards deep learning models resistant to adversarial attacks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.028850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e5d04049-26ad-4403-ac64-5d880fb7bef2 · outbound

This paper cites Connecting certified and adversarial training.

Improving Certified Robustness via Adversarial Distillation Connecting certified and adversarial training

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.052802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 868bacc5-b97a-436f-9cc6-09d48dfa074d · outbound

This paper cites Understanding certified training with interval bound propagation.

Improving Certified Robustness via Adversarial Distillation Understanding certified training with interval bound propagation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.036571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9a450ff5-e50e-4557-993c-989cef480add · outbound

This paper cites Ctbench: A library and benchmark for certified training.

Improving Certified Robustness via Adversarial Distillation Ctbench: A library and benchmark for certified training

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.967830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation adb684e1-c67a-4448-be04-7dda8cf1e22c · outbound

This paper cites Differentiable abstract interpretation for provably robust neural networks.

Improving Certified Robustness via Adversarial Distillation Differentiable abstract interpretation for provably robust neural networks

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.979631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 603ea08b-7ee7-4382-a941-6e69d26519be · outbound

This paper cites Certified training: Small boxes are all you need.

Improving Certified Robustness via Adversarial Distillation Certified training: Small boxes are all you need

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.063495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c0e5c7b-5557-453c-8a8f-5a1deabc7720 · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library.

Improving Certified Robustness via Adversarial Distillation Pytorch: An imperative style, high-performance deep learning library

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.997453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9392de4c-778d-44b9-a30b-3c67129b573e · outbound

This paper cites Fast certified robust training with short warmup.

Improving Certified Robustness via Adversarial Distillation Fast certified robust training with short warmup

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.025460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e9a72c9d-ee6b-4e47-bd15-07295d1ab241 · outbound

This paper cites An abstract domain for certifying neural networks.Proc.

Improving Certified Robustness via Adversarial Distillation An abstract domain for certifying neural networks.Proc

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.043215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3dec6767-dde2-40ff-95a1-dcae688026e0 · outbound

This paper cites Intriguing properties of neural networks.

Improving Certified Robustness via Adversarial Distillation Intriguing properties of neural networks

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.037605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4e867a8b-4f82-448c-b150-69c7df6fede5 · outbound

This paper cites Evaluating robustness of neural networks with mixed integer programming.

Improving Certified Robustness via Adversarial Distillation Evaluating robustness of neural networks with mixed integer programming

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.039446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 930f5377-b45d-434a-a6c5-e253e82c86ae · outbound

This paper cites On adaptive attacks to adversarial example defenses.

Improving Certified Robustness via Adversarial Distillation On adaptive attacks to adversarial example defenses

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.041126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b45458b1-82cd-49ad-829c-34edee1df26d · outbound

This paper cites Beta-CROWN: Efficient bound propagation with per-neuron split constraints for complete and incomplete neural network verification.

Improving Certified Robustness via Adversarial Distillation Beta-CROWN: Efficient bound propagation with per-neuron split constraints for complete and incomplete neural network verification

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.046982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2360f043-58a2-4074-9fe6-6e3a6a814c5d · outbound

This paper cites Zico Kolter.

Improving Certified Robustness via Adversarial Distillation Zico Kolter

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.991620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 16fc48f5-b9a5-4676-ab17-eaaf4fdc4392 · outbound

This paper cites Automatic perturbation analysis for scalable certified robustness and beyond.Advances in Neural Information Processing Systems, 2020.

Improving Certified Robustness via Adversarial Distillation Automatic perturbation analysis for scalable certified robustness and beyond.Advances in Neural Information Processing Systems, 2020

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.029580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5b805d12-2b85-472f-ae14-934c86f32df5 · outbound

This paper cites Fast and Complete: Enabling complete neural network verification with rapid and massively parallel incomplete verifiers.

Improving Certified Robustness via Adversarial Distillation Fast and Complete: Enabling complete neural network verification with rapid and massively parallel incomplete verifiers

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.033926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1518904c-4873-45e8-adfd-6bff78189075 · outbound

This paper cites Rethinking lipschitz neural networks and certified robustness: A boolean function perspective.

Improving Certified Robustness via Adversarial Distillation Rethinking lipschitz neural networks and certified robustness: A boolean function perspective

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.047920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 383acd68-578a-4a23-a780-22e191f4eac9 · outbound

This paper cites Boosting the certified robustness of l-infinity distance nets.

Improving Certified Robustness via Adversarial Distillation Boosting the certified robustness of l-infinity distance nets

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.045023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 969d7fbf-d306-4c41-baeb-6387511176c6 · outbound

This paper cites Efficient neural network robustness certification with general activation functions.

Improving Certified Robustness via Adversarial Distillation Efficient neural network robustness certification with general activation functions

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.031858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 700a03ba-0725-40fd-a3d4-954653563a76 · outbound

This paper cites Towards stable and efficient training of verifiably robust neural networks.

Improving Certified Robustness via Adversarial Distillation Towards stable and efficient training of verifiably robust neural networks

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.977388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8fd583a5-f43a-40fa-bdca-e4c75db59d60 · outbound

This paper cites General cutting planes for bound-propagation-based neural network verification.

Improving Certified Robustness via Adversarial Distillation General cutting planes for bound-propagation-based neural network verification

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.018802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a2af17b3-335c-4a76-8ba5-7b91f0d760ae · outbound

This paper cites Generating less certain adversarial examples improves robust generalization.Transactions on Machine Learning Research, 2025.

Improving Certified Robustness via Adversarial Distillation Generating less certain adversarial examples improves robust generalization.Transactions on Machine Learning Research, 2025

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.045761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 674ad7f2-58b0-43c6-84ec-bcc139a2f002 · outbound

This paper cites Reliable adversarial distillation with unreliable teachers.

Improving Certified Robustness via Adversarial Distillation Reliable adversarial distillation with unreliable teachers

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.030726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e7ccb5c1-1910-42ef-b131-bf9d38c21a6a · outbound

This paper cites Revisiting adversarial robustness distillation: Robust soft labels make student better.

Improving Certified Robustness via Adversarial Distillation Revisiting adversarial robustness distillation: Robust soft labels make student better

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:50.984501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 31719d8e-bc52-4076-a52c-d7366d112280 · outbound

This paper cites [29], with weight 0.5 on MNIST and CIFAR-10, and 0.2 on TinyImageNet, during warmup.

Improving Certified Robustness via Adversarial Distillation [29], with weight 0.5 on MNIST and CIFAR-10, and 0.2 on TinyImageNet, during warmup

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.005915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 83203196-fbda-4141-90c9-ff8c897949f2 · outbound

This paper cites an unresolved cited work.

Improving Certified Robustness via Adversarial Distillation Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-07-06T19:12:51.021004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4c76dda3-0705-4e6d-938e-dc0f03d2da81 · outbound

This paper cites The final hyperparameters used for AD-CERT across all settings are reported in Table 6.

Improving Certified Robustness via Adversarial Distillation The final hyperparameters used for AD-CERT across all settings are reported in Table 6

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T19:12:51.023586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

No inbound Pith citation observations are available.