Securing LLMs in the Wild: Privacy and Security Challenges at the Edge | Paper Citation Record

Observation a922672d-5224-4d88-a345-6eddc15155b8 · outbound

This paper cites Security and privacy challenges of large language models: A survey.ACM Computing Surveys, 57(6):1–39, 2025.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Security and privacy challenges of large language models: A survey.ACM Computing Surveys, 57(6):1–39, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:13.010889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d577685-e90a-41a6-8ae1-cdb9881a11d6 · outbound

This paper cites an unresolved cited work.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:13.102954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a517f81-26a5-4fcd-b2d7-249a8a58d79d · outbound

This paper cites Department of Health and Human Services.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Department of Health and Human Services

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:13.205852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b2cbe34-ab2f-4136-a24d-8af7345cc739 · outbound

This paper cites Regulation (EU) 2024/1689 of the European Parliament and of the Council Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act).

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Regulation (EU) 2024/1689 of the European Parliament and of the Council Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act)

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:13.491779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb9a3507-15a3-4772-b0b5-25a4c9f61d73 · outbound

This paper cites Removing Barriers to American Leadership in Artificial Intelligence.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Removing Barriers to American Leadership in Artificial Intelligence

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:13.647492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21381d3b-51a1-46d8-ab7b-86d29a4870d3 · outbound

This paper cites Strengthening our frontier safety framework.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Strengthening our frontier safety framework

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:13.769394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8cd93f3-4f1a-412a-b31a-5c5f762b48c5 · outbound

This paper cites Deploying llm transformer on edge computing devices: A survey of strategies, challenges, and future directions.AI, 7(1):15, 2026.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Deploying llm transformer on edge computing devices: A survey of strategies, challenges, and future directions.AI, 7(1):15, 2026

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:13.969226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f93c1a17-2824-4ed0-9be1-ec68c7debd82 · outbound

This paper cites an unresolved cited work.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.081695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cd713f8-830e-4204-8099-193607921a5c · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Efficient memory management for large language model serving with pagedattention

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.198426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76499889-b987-4f30-93af-051bc233843c · outbound

This paper cites Advancing practical homomorphic encryption for federated learning: Theoretical guarantees and efficiency optimizations.arXiv preprint arXiv:2509.20476, 2025.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Advancing practical homomorphic encryption for federated learning: Theoretical guarantees and efficiency optimizations.arXiv preprint arXiv:2509.20476, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.303849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b4d34a-eff4-499c-8542-12532d7b1d55 · outbound

This paper cites Zeroquant: Efficient and affordable post- training quantization for large-scale transformers.Advances in neural information processing systems, 35:27168–27183, 2022.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Zeroquant: Efficient and affordable post- training quantization for large-scale transformers.Advances in neural information processing systems, 35:27168–27183, 2022

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.442437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f74e88df-bd47-4335-b08e-607fa27abc0a · outbound

This paper cites Exploiting llm quantization.Advances in Neural Information Processing Systems, 37:41709–41732, 2024.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Exploiting llm quantization.Advances in Neural Information Processing Systems, 37:41709–41732, 2024

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.601915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bef5eab-2f20-4152-a455-477850d34f6b · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Explaining and Harnessing Adversarial Examples

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.781159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 385e11d0-06ce-46f2-9aa3-b6deae1f5afb · outbound

This paper cites Attacking Binarized Neural Networks.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Attacking Binarized Neural Networks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.896441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ece4f88-45ae-4db5-b916-eb355ecf00b6 · outbound

This paper cites Synthesizing robust adversarial examples.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Synthesizing robust adversarial examples

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.899199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f1dbe98-401c-4ad7-a6ed-0ee53e0b7228 · outbound

This paper cites Quantization aware attack: Enhancing transferable adversarial attacks by model quantization.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Quantization aware attack: Enhancing transferable adversarial attacks by model quantization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.902096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9707a9e-7d3e-4876-9480-ba6fe09395d7 · outbound

This paper cites On jailbreaking quantized language models through fault injection attacks.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge On jailbreaking quantized language models through fault injection attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.904935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98c800fa-02e5-44c4-ab27-439967470c2c · outbound

This paper cites Quantization-based jailbreaking vulnerability analysis: A study on performance and safety of the llama3-8b-instruct model.IEEE Access, 2025.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Quantization-based jailbreaking vulnerability analysis: A study on performance and safety of the llama3-8b-instruct model.IEEE Access, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.907375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c786fd67-6811-44e5-a0e4-47fdd0fc3a66 · outbound

This paper cites Flipping bits in memory without accessing them: An experimental study of dram disturbance errors.ACM SIGARCH Computer Architecture News, 42(3):361–372, 2014.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Flipping bits in memory without accessing them: An experimental study of dram disturbance errors.ACM SIGARCH Computer Architecture News, 42(3):361–372, 2014

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.909827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b07c5533-8b8a-40a5-946c-de087c1f61ab · outbound

This paper cites Bit-flip attack: Crushing neural network with progressive bit search.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Bit-flip attack: Crushing neural network with progressive bit search

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.912258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0104b93-7d1f-4b2f-abe6-8026f745c0bf · outbound

This paper cites Deep reinforcement learning from human prefer- ences.Advances in neural information processing systems, 30, 2017.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Deep reinforcement learning from human prefer- ences.Advances in neural information processing systems, 30, 2017

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.915099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95844534-4e5a-471e-9851-714a65f47d10 · outbound

This paper cites Learning to summarize with human feedback.Advances in neural information processing systems, 33:3008–3021, 2020.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Learning to summarize with human feedback.Advances in neural information processing systems, 33:3008–3021, 2020

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.917641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6036cab6-df6d-4bc5-acdd-f3e0541b911f · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741, 2023.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741, 2023

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.920032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77e60fdf-6646-47d2-aaeb-7d4a8650fda7 · outbound

This paper cites Safety alignment should be made more than just a few tokens deep.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Safety alignment should be made more than just a few tokens deep

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.922432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1413985e-a75b-42c4-b4dd-4eb5327cd5e8 · outbound

This paper cites The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.924793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 872934e3-2ea7-46e5-8f31-63e3bd86b54f · outbound

This paper cites A simple and effective pruning approach for large language models.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge A simple and effective pruning approach for large language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.927848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 960cab5f-cbbc-416a-b0d1-6b2fef3c4e32 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models.Advances in neural information processing systems, 36:21702–21720, 2023.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Llm-pruner: On the structural pruning of large language models.Advances in neural information processing systems, 36:21702–21720, 2023

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.930824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcc8117c-adf3-4adc-a3af-4b28f7f06d9f · outbound

This paper cites Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.933979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76edfb29-ef8c-4681-b385-613713670a63 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.936549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8379b3b1-9257-4288-b01a-fc704ffb8998 · outbound

This paper cites Are sixteen heads really better than one?Advances in neural information processing systems, 32, 2019.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Are sixteen heads really better than one?Advances in neural information processing systems, 32, 2019

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.938619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c90bfd3-a5db-4c70-8f38-0575b9e87fb7 · outbound

This paper cites Palu: Compressing KV-Cache with Low-Rank Projection.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Palu: Compressing KV-Cache with Low-Rank Projection

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.941014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e246d9ea-7eb0-4ec5-8390-8d4c7fb5064b · outbound

This paper cites When efficiency meets safety: A benchmark security analysis of kv cache compression in large language models.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge When efficiency meets safety: A benchmark security analysis of kv cache compression in large language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.944115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f5fa137-025a-4000-b0d2-b8dc23fe93fc · outbound

This paper cites Pruning for protection: Increasing jailbreak resistance in aligned llms without fine-tuning.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Pruning for protection: Increasing jailbreak resistance in aligned llms without fine-tuning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.946177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4b4fb82-c456-4066-b07d-2e513f04895a · outbound

This paper cites Edgeshard: Efficient llm inference via collaborative edge com- puting.IEEE Internet of Things Journal, 12(10):13119–13131, 2024.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Edgeshard: Efficient llm inference via collaborative edge com- puting.IEEE Internet of Things Journal, 12(10):13119–13131, 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.948403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1ff58ae-9b9a-4a73-a191-d45db88330ba · outbound

This paper cites Attacking and protecting data privacy in edge–cloud collaborative inference systems.IEEE Internet of Things Journal, 8(12):9706–9716, 2020.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Attacking and protecting data privacy in edge–cloud collaborative inference systems.IEEE Internet of Things Journal, 8(12):9706–9716, 2020

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.950716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8a1084d-7083-41ac-b12e-628a39063657 · outbound

This paper cites Prompt inference attack on distributed large language model inference frameworks.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Prompt inference attack on distributed large language model inference frameworks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.953280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f373b04-6fea-4e77-87e3-e37235906883 · outbound

This paper cites Algen: Few-shot inversion attacks on textual embeddings via cross-model alignment and generation.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Algen: Few-shot inversion attacks on textual embeddings via cross-model alignment and generation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.955579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2a75ed-3bc1-4a1b-a618-fef9c0aa9e26 · outbound

This paper cites Calibrating noise to sensitivity in private data analysis.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Calibrating noise to sensitivity in private data analysis

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.957709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42e204af-43c3-492a-9c40-4ccb97241f7c · outbound

This paper cites Qlora: Efficient finetuning of quantized llms.Advances in neural information processing systems, 36:10088–10115, 2023.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Qlora: Efficient finetuning of quantized llms.Advances in neural information processing systems, 36:10088–10115, 2023

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.959942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a251a6c-54e5-4e13-b3b3-1d9cd6d62972 · outbound

This paper cites Lora: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Lora: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.962477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4fa1a3c-8115-45f0-97fb-ffcea8d72180 · outbound

This paper cites Lora as oracle.arXiv preprint arXiv:2601.11207, 2026.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Lora as oracle.arXiv preprint arXiv:2601.11207, 2026

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.965090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0092ce85-4f66-4a2e-bd4f-de31dfc399bf · outbound

This paper cites Membership inference attacks against machine learning models.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Membership inference attacks against machine learning models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.967390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12cf418e-e97f-41a7-8a4a-2c5d08e676dc · outbound

This paper cites Extracting training data from large language models.USENIX Security Symposium, 2021.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Extracting training data from large language models.USENIX Security Symposium, 2021

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.969882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afdf589a-7001-4f4e-a4fa-bcc8ea57b266 · outbound

This paper cites Quantifying memorization across neural language models.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Quantifying memorization across neural language models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.972037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bd3997a-6540-4d72-843e-f570b4e3bf0d · outbound

This paper cites Morris Chang.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Morris Chang

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.973954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef8642be-d38a-4aff-8f21-4d3470192fa4 · outbound

This paper cites Federated fine-tuning of large language models under heterogeneous tasks and client resources.Advances in Neural Information Processing Systems, 37:14457–14483, 2024.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Federated fine-tuning of large language models under heterogeneous tasks and client resources.Advances in Neural Information Processing Systems, 37:14457–14483, 2024

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.976040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d15a141-5233-4d50-8c22-d5457d594a32 · outbound

This paper cites Deep leakage from gradients.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Deep leakage from gradients

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.977958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae42c21c-08ab-44bd-95f9-d9d81d119188 · outbound

This paper cites AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.980087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b83f6a36-3faa-49c0-be23-dbe3aa984f5c · outbound

This paper cites Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.982394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 798acf14-67e8-491c-97d5-705bb7873ef1 · outbound

This paper cites Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.984239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c386bdd-6e23-429f-9a72-7d91beed3539 · outbound

This paper cites Certified adversarial robustness via randomized smoothing.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Certified adversarial robustness via randomized smoothing

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.986570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14f5019f-ebf1-4edf-8e5b-c2ae4dff5514 · outbound

This paper cites What disease does this patient have? a large-scale open domain question answering dataset from medical exams.Applied Sciences, 11(14):6421, 2021.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge What disease does this patient have? a large-scale open domain question answering dataset from medical exams.Applied Sciences, 11(14):6421, 2021

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.989110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 828c5745-a6bd-48a6-b295-bbc4312cd9ef · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Measuring Massive Multitask Language Understanding

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.991226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0dcf847-6034-4691-b985-2e791ab2b8ab · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Evaluating Large Language Models Trained on Code

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.993630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 100a7419-c880-4902-a5f0-46ee9b3a4b7f · outbound

This paper cites Edge-mpq: Layer-wise mixed-precision quantization with tightly integrated versatile inference units for edge computing.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Edge-mpq: Layer-wise mixed-precision quantization with tightly integrated versatile inference units for edge computing

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.996408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8962cff8-a341-4289-bb8b-2627367d7411 · outbound

This paper cites Measuring massive multitask language understanding.Proceedings of the International Conference on Learning Representations (ICLR), 2021.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Measuring massive multitask language understanding.Proceedings of the International Conference on Learning Representations (ICLR), 2021

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:14.998969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26c56a31-2f03-48a2-a95f-19906133c62c · outbound

This paper cites Measuring massive mul- titask language understanding (github repository).

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Measuring massive mul- titask language understanding (github repository)

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:15.001295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 011e9db7-1450-42c9-b31c-a9428774f455 · outbound

This paper cites Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:15.003575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f670b255-91ac-4750-bdf5-8fc1f7319787 · outbound

This paper cites Qwen2.5-Coder Technical Report.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Qwen2.5-Coder Technical Report

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:15.006812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 702a0fdd-ec96-411a-99d2-82532e8027f9 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Gemma 2: Improving Open Language Models at a Practical Size

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:15.009992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 031f8c2a-8541-4c99-b4fa-a7fb2983150e · outbound

This paper cites Gemma 4 technical report, 2026.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Gemma 4 technical report, 2026

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:15.012910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17129004-a3d0-41c4-bf9a-e9888be7792b · outbound

This paper cites The Llama 3 Herd of Models.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge The Llama 3 Herd of Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:15.015602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a41ea142-031b-4be5-b8c6-ad37ded71a54 · outbound

This paper cites Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:15.018313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f4f0e1a-a9fc-4678-8c71-5b184f558fc6 · outbound

This paper cites Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T06:50:15.020939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8e46e0-ddb2-423c-ada0-afefc8b9dc17 · outbound

This paper cites an unresolved cited work.

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge Unresolved cited work

Reference 2002

Resolution: parse uncertain; no resolver link, observed 2026-08-02T06:50:13.359014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers