LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats | Paper Citation Record

Observation fa46251d-ef93-4909-97f0-a9ae46ffb811 · outbound

This paper cites Maity and Manob Jyoti Saikia.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Maity and Manob Jyoti Saikia

Reference 1

Resolution: malformed identifier; no resolver link, observed 2026-08-02T10:25:16.570269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99563142-e008-46ba-8b00-0bba84d8af40 · outbound

This paper cites Yuan et al.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Yuan et al

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:16.635328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 264ac16a-b9c0-40a2-89c2-190168f8b4fd · outbound

This paper cites Vrdoljak, Z.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Vrdoljak, Z

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:16.745416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9726b673-973b-4067-8483-1e4700456697 · outbound

This paper cites A systematic review of transformer-based pre-trained language models through self-supervised learn- ing.Information, 14(3):187, 2023.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats A systematic review of transformer-based pre-trained language models through self-supervised learn- ing.Information, 14(3):187, 2023

Reference 4

Resolution: verified exact; doi, observed 2026-08-02T10:28:44.479446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a53d861e-38a5-4a9b-bf3d-ec66583f76b9 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:16.966253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1838a58-0193-48a8-9018-848370290388 · outbound

This paper cites Quantifying memorization across neural language models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Quantifying memorization across neural language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:17.120667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 201ba6aa-6fc0-4f95-90fe-3753c1027d00 · outbound

This paper cites Karamolegkou, J.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Karamolegkou, J

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:17.214496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e7bef13-ae7f-44c4-b255-9e1f1577c779 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:17.314524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d64e373-59ba-4182-affd-487640e9f4c7 · outbound

This paper cites Jailbroken: How does llm safety training fail? InNeurIPS, 2023.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Jailbroken: How does llm safety training fail? InNeurIPS, 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:17.470923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fc5e5ad-2f53-4a2f-a4cd-03b78848db95 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:17.558849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6248d9bf-5e1a-4d89-9664-7cc0eaf7cc74 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:17.650340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce297a2-006e-43d7-a57c-5abe72b29b25 · outbound

This paper cites Lizzo and L.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Lizzo and L

Reference 12

Resolution: verified exact; doi, observed 2026-08-02T10:28:44.124743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7bc9d295-4123-482e-9ad4-7381521f811d · outbound

This paper cites Zhang et al.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Zhang et al

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:17.957095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60f8e9f-370d-4195-a3d9-387f7e5420c1 · outbound

This paper cites A review on machine unlearning.SN Computer Science, 4(4), 2023.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats A review on machine unlearning.SN Computer Science, 4(4), 2023

Reference 14

Resolution: verified exact; doi, observed 2026-08-02T10:28:43.838085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d9cb1325-11a4-4da7-9076-30b40e272c23 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 15

Resolution: malformed identifier; no resolver link, observed 2026-08-02T10:25:18.149505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ba21e2-4735-4456-be66-79f0bee97cf9 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 16

Resolution: malformed identifier; no resolver link, observed 2026-08-02T10:25:18.231323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a498fe1d-7d4e-4558-ba08-a6476dfeae32 · outbound

This paper cites A survey on large language models unlearning: Taxonomy, evaluations, and future directions.Artificial Intelligence Review, 58 (12), 2025.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats A survey on large language models unlearning: Taxonomy, evaluations, and future directions.Artificial Intelligence Review, 58 (12), 2025

Reference 17

Resolution: verified exact; doi, observed 2026-08-02T10:28:44.301427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3dc9de48-3a19-42d2-b9df-5fce5f7955ab · outbound

This paper cites Cevallos, Marco E.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Cevallos, Marco E

Reference 18

Resolution: verified exact; doi, observed 2026-08-02T10:28:43.722187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6f77eb21-b3fe-436c-8139-20ad45edfd8f · outbound

This paper cites Towards making systems forget with machine unlearning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Towards making systems forget with machine unlearning

Reference 19

Resolution: verified exact; doi, observed 2026-08-02T10:28:43.575727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 426e7665-c258-4fe7-99ff-4cbd53808ff6 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:18.633561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf7d06db-0d6e-485a-b07d-5cd5d7123559 · outbound

This paper cites An Adversarial Perspective on Machine Unlearning for AI Safety.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats An Adversarial Perspective on Machine Unlearning for AI Safety

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:18.726548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c5a9169-df54-4aa1-a754-0e5fab6a8214 · outbound

This paper cites Magesh, F.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Magesh, F

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:18.802703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfdac604-f989-43ee-aa32-80f20d9d578c · outbound

This paper cites Adversar- ial machine learning: A taxonomy and terminology of attacks and mitigations.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Adversar- ial machine learning: A taxonomy and terminology of attacks and mitigations

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:18.945042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13aa35f1-e700-429f-b442-32b1607dbc7a · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.132447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfbf620b-bf45-46e6-a81d-0f64d33252ab · outbound

This paper cites Schwinn, D.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Schwinn, D

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.250354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6fdc2fb-c971-4325-9a7b-17772c5ae30b · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.001977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecd9c4aa-cc7d-493f-ab91-c9fc95f46bbc · outbound

This paper cites Provvedimento del 30 marzo 2023 [9870832].

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Provvedimento del 30 marzo 2023 [9870832]

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.437728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5db8cabb-2a25-4a57-93bc-650ffbe55c64 · outbound

This paper cites The EU proposal for a general data protection regulation and the roots of the right to be forgotten.Computer Law and Security Review, 29(3):229–235, 2013.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats The EU proposal for a general data protection regulation and the roots of the right to be forgotten.Computer Law and Security Review, 29(3):229–235, 2013

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.490858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82d90913-3c15-4dcd-a027-79802318485c · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.347791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 111f8706-fa3b-45f5-88ea-8d71ed22fe16 · outbound

This paper cites Do large language models understand us?Daedalus, 151(2):183–197, 2022.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Do large language models understand us?Daedalus, 151(2):183–197, 2022

Reference 30

Resolution: malformed identifier; doi_truncated, observed 2026-08-02T10:28:43.364904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4b7b1dc6-829e-4338-a4dd-1082e471fe19 · outbound

This paper cites Naveed et al.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Naveed et al

Reference 31

Resolution: verified exact; doi, observed 2026-08-02T10:28:43.132574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 751579c0-37f7-47cb-9971-80ee7772ebb0 · outbound

This paper cites Moffatt v.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Moffatt v

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.579973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7926a3e7-342c-4cd9-b8f7-a7b3e6ff8a89 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Bert: Pre-training of deep bidirectional transformers for language understanding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.719842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd2498da-d34b-4aa3-9a3c-223c17f4b185 · outbound

This paper cites Liu et al.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Liu et al

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.721917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aada7cfc-2310-4689-978d-c76866032130 · outbound

This paper cites Improving language understanding by generative pre-training, 2018.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Improving language understanding by generative pre-training, 2018

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.717663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d2d9695-e579-4cfb-b8a3-b903bd7025c9 · outbound

This paper cites Language models are few-shot learners.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Language models are few-shot learners

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.726114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b27776a1-0f93-489b-b9f5-46ab07706f31 · outbound

This paper cites Palm: Scaling language modeling with pathways.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Palm: Scaling language modeling with pathways

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.728057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6db1812b-8cf2-4358-a160-f0f24f0e5c36 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 38

Resolution: verified exact; doi, observed 2026-08-02T10:28:42.980643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bf27a497-6633-4c5c-86aa-d24e2bf19f91 · outbound

This paper cites Fields, K.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Fields, K

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.732609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea214d8-dd63-4b8a-aa74-60c9886b4e27 · outbound

This paper cites Peykani, F.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Peykani, F

Reference 40

Resolution: malformed identifier; no resolver link, observed 2026-08-02T10:25:19.734591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6de2f49b-14a6-4a01-8238-4693a832c569 · outbound

This paper cites Acharya, B.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Acharya, B

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.730381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb00a1f1-6fb9-4dcf-985d-9621cd2cb391 · outbound

This paper cites Transformer feed- forward layers are key-value memories.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Transformer feed- forward layers are key-value memories

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.739031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9869d85-edfb-4570-8df5-aa4b5557d938 · outbound

This paper cites Locating and editing factual associations in gpt.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Locating and editing factual associations in gpt

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.741653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93b9e5ab-fdc2-4432-b812-2319a81e1cbd · outbound

This paper cites Trust and R.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Trust and R

Reference 44

Resolution: verified exact; doi, observed 2026-08-02T10:28:42.795281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e1e24d3d-ead1-4f6b-9b82-80c448286845 · outbound

This paper cites Machine unlearning: Solu- tions and challenges.IEEE Transactions on Emerging Topics in Computational Intelligence, 8(3):2150–2168, 2024.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Machine unlearning: Solu- tions and challenges.IEEE Transactions on Emerging Topics in Computational Intelligence, 8(3):2150–2168, 2024

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.751218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d85927f2-430c-42e5-8c1e-ae46f5a92d64 · outbound

This paper cites Arcane: An efficient architecture for exact machine unlearning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Arcane: An efficient architecture for exact machine unlearning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.753336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04a63d7b-9eec-408d-a296-c2d21e8972dd · outbound

This paper cites Roy, and Gintare Karolina Dziugaite.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Roy, and Gintare Karolina Dziugaite

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.748338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5366dc64-99ad-49ab-9a8f-86131dbb03eb · outbound

This paper cites Unlearning vs.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unlearning vs

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.758280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb68027a-d157-4eed-9564-1fcfa3f8b1a4 · outbound

This paper cites Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.760634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 843d8674-213b-49be-af00-1ec75328dec1 · outbound

This paper cites Certified Data Removal from Machine Learning Models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Certified Data Removal from Machine Learning Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.755541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49a5c638-b19c-4926-83a9-ef910dad7bc9 · outbound

This paper cites Eternal sunshine of the spotless net: Selective forgetting in deep networks.IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Eternal sunshine of the spotless net: Selective forgetting in deep networks.IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.765227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa2fba3f-dd0c-4094-adb4-2b731f103721 · outbound

This paper cites $\nabla \tau$: Gradient-based and Task-Agnostic machine Unlearning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats $\nabla \tau$: Gradient-based and Task-Agnostic machine Unlearning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.767300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa8f8cb2-fd3a-4211-87bd-b0e81d1b2b3e · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.763135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f836d51-2542-462c-958b-3e7e2c0026f6 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.772350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70008ea7-f51e-4fd7-8cd1-41e2877f7e27 · outbound

This paper cites Towards fair large language model-based recommender systems without costly retraining.arXiv preprint arXiv:2601.17492, 2026.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Towards fair large language model-based recommender systems without costly retraining.arXiv preprint arXiv:2601.17492, 2026

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.774422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d4ab7a5-449f-4520-8964-e80ce91fdaf0 · outbound

This paper cites LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.769627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c07710b4-0dcd-4441-b486-005afbd2e045 · outbound

This paper cites Forget the token and pixel: Rethinking gradient ascent for concept unlearning in multimodal generative models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Forget the token and pixel: Rethinking gradient ascent for concept unlearning in multimodal generative models

Reference 57

Resolution: malformed identifier; no resolver link, observed 2026-08-02T10:25:19.778586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 563802c9-df03-4c4d-b061-83e10453981d · outbound

This paper cites Is gradient ascent really necessary? memorize to forget for machine unlearning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Is gradient ascent really necessary? memorize to forget for machine unlearning

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.780768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a19558f-2564-4793-b5e7-2d3393c31f4f · outbound

This paper cites Unified gradient-based machine unlearning with remain geometry enhancement.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unified gradient-based machine unlearning with remain geometry enhancement

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.776459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf57099b-aaa5-4b11-b3fe-d05271a07453 · outbound

This paper cites Mass-Editing Memory in a Transformer.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Mass-Editing Memory in a Transformer

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.784681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aba463ea-85de-4889-80c2-77b9307c5b78 · outbound

This paper cites Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.787330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91950104-b32a-4a28-b9b8-d653bfe6e33f · outbound

This paper cites Fine-grained pluggable gradient ascent for knowledge unlearning in language models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Fine-grained pluggable gradient ascent for knowledge unlearning in language models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.782741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b99fae-bd69-4be6-aa11-ba0c49843be2 · outbound

This paper cites Forget for get: A lightweight two-phase gradient method for knowledge editing in large language models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Forget for get: A lightweight two-phase gradient method for knowledge editing in large language models

Reference 63

Resolution: verified exact; doi, observed 2026-08-02T10:28:42.521666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation eeeaa61a-d127-42b3-a7f3-b54186256b51 · outbound

This paper cites Fg- oriu: Towards better forgetting via feature-gradient orthogonality for incremental unlearning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Fg- oriu: Towards better forgetting via feature-gradient orthogonality for incremental unlearning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.797094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3704d76a-2997-449e-a948-0b17d83f6196 · outbound

This paper cites SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.789536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 475cc74c-cada-4b9e-94c7-e4fc20cda888 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.803640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a4e3884-1f33-4a8b-8d32-0899a363f21e · outbound

This paper cites LLM unlearning with LLM beliefs.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats LLM unlearning with LLM beliefs

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.806191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a453114-d879-4c1c-ac0a-bca715c8de70 · outbound

This paper cites Negative preference optimiza- tion: From catastrophic collapse to effective unlearning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Negative preference optimiza- tion: From catastrophic collapse to effective unlearning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.799207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a1acb01-c4e2-41f2-9327-e4c2612b94c2 · outbound

This paper cites Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.801241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bda05b58-244c-4538-9744-957671d786a4 · outbound

This paper cites Stable for- getting: Bounded parameter-efficient unlearning in foundation models, 2026.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Stable for- getting: Bounded parameter-efficient unlearning in foundation models, 2026

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.816923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56db4fd6-693c-4c94-8ba2-e40d28f4dcee · outbound

This paper cites Levi, and Volkan Cevher.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Levi, and Volkan Cevher

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.819345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89dac873-f3d3-4aaa-9f4e-bea013ab3306 · outbound

This paper cites Forgetting-MarI: LLM unlearning via marginal information regularization, 2026.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Forgetting-MarI: LLM unlearning via marginal information regularization, 2026

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.812111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 730e09b7-b3d6-477a-b39c-36454dc0b320 · outbound

This paper cites Label smoothing improves gradient ascent in LLM unlearning, 2025.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Label smoothing improves gradient ascent in LLM unlearning, 2025

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.814314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b74dff57-557c-46d1-81a1-5a50916a063a · outbound

This paper cites GRAIL: Gradient-based adaptive unlearning for privacy and copyright in LLMs, 2025.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats GRAIL: Gradient-based adaptive unlearning for privacy and copyright in LLMs, 2025

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.828124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d8fe6cd-eb2f-43d5-9a05-5488eac40143 · outbound

This paper cites CATNIP: LLM unlearning via calibrated and tokenized nega- tive preference alignment, 2026.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats CATNIP: LLM unlearning via calibrated and tokenized nega- tive preference alignment, 2026

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.830229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb2d15ad-8499-4af6-b361-ab14ef0dc815 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.821594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 176ee119-25c1-46d0-954b-c85682540813 · outbound

This paper cites Transformer feed- forward layers are key-value memories.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Transformer feed- forward layers are key-value memories

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.823761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a63f034-1401-47c5-95d7-c04f884da692 · outbound

This paper cites Machine Unlearning in Contrastive Learning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Machine Unlearning in Contrastive Learning

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.825901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99a8e40f-f5ab-470b-b8a5-cb11e6b59679 · outbound

This paper cites Gauss-newton unlearning for the llm era.arXiv preprint arXiv:2602.10568, 2026.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Gauss-newton unlearning for the llm era.arXiv preprint arXiv:2602.10568, 2026

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.838908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d51513d1-7b8a-4c27-98ba-2b5d92724f12 · outbound

This paper cites Lacuna inc.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Lacuna inc

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.840919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31e076e9-a0a3-4940-a1a6-90849d33cf6f · outbound

This paper cites Training data influence analysis and esti- mation: A survey.Machine Learning, 2024.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Training data influence analysis and esti- mation: A survey.Machine Learning, 2024

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.832286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5835f582-8e0b-48b6-b8c5-e4afede69bdd · outbound

This paper cites Adapting and evaluating influence-estimation methods for gradient-boosted decision trees.Journal of Machine Learning Research, 24:1–48, 2023.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Adapting and evaluating influence-estimation methods for gradient-boosted decision trees.Journal of Machine Learning Research, 24:1–48, 2023

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.834409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8434a79-0da1-4053-92f8-3f669f3100e2 · outbound

This paper cites IMU: Influence-guided Machine Unlearning.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats IMU: Influence-guided Machine Unlearning

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.836437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 420f68ab-b360-416d-8a6c-4c9be65d4d5f · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 84

Resolution: verified exact; doi, observed 2026-08-02T10:28:42.323851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 938bcffe-d357-453e-bb59-2c175f70116f · outbound

This paper cites Cheng, Y.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Cheng, Y

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.851619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce47a568-5097-4eb7-8627-2677f875f077 · outbound

This paper cites Influence functions in deep learning are fragile.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Influence functions in deep learning are fragile

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.842918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 210ac0d3-ae91-445b-b07b-308a1e12e4ed · outbound

This paper cites Can sensitive information be deleted from llms? objectives for defending against extraction attacks.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Can sensitive information be deleted from llms? objectives for defending against extraction attacks

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.845193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 571f9980-0a00-4571-8755-f8f594ac37d1 · outbound

This paper cites Cheng, P.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Cheng, P

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.847283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36a8ff34-bac7-416e-9dfd-7795da458077 · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.860739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d140652-9560-499e-aa48-9d6e662ac0b9 · outbound

This paper cites Fast Model Editing at Scale.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Fast Model Editing at Scale

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.863051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1be90ea5-d999-4932-bcae-299a36a70d76 · outbound

This paper cites Luo, Z.-H.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Luo, Z.-H

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.853786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2e56f23-8eac-4e81-8900-fa1e7322a28c · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.856229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 106b7e5b-abc0-417b-bcf8-96a52b4fb70d · outbound

This paper cites an unresolved cited work.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Unresolved cited work

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.858444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 157bd3c1-10d4-45ef-960a-1d40cae9d861 · outbound

This paper cites Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.874767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac8843de-d1f1-4a2d-842b-ea1d8aa07d25 · outbound

This paper cites DP2Unlearning: An efficient and guaranteed unlearning framework for LLMs.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats DP2Unlearning: An efficient and guaranteed unlearning framework for LLMs

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.877915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d7402fa-b196-4526-9dd8-4b5472b20bc9 · outbound

This paper cites WISE: Rethinking the knowledge memory for lifelong model editing of large language models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats WISE: Rethinking the knowledge memory for lifelong model editing of large language models

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.865376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f1a675d-68ec-4a4f-a9bc-d768b62ef455 · outbound

This paper cites WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.867614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ea6c0fc-519d-44bf-9d8a-ccd31a6c1893 · outbound

This paper cites AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.870177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2de0a96-9bc4-4995-956f-b9bf1327d3e5 · outbound

This paper cites PMET: Precise model editing in a transformer.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats PMET: Precise model editing in a transformer

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.872583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fabcbdac-be28-4933-8582-6b21824ebb61 · outbound

This paper cites Laguna, J.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Laguna, J

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.889401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers