Paper Citation Record · LEDGER

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

As of 9 August 2026, this Paper Citation Record lists 100 of 259 outbound references and 13 inbound Pith citation observations for arXiv:2502.05224.

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

pith.paper-citation-record.v1
2502.05224 v1

Coverage vector

measured 100 of 259 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T00:50:00.427377Z

measured 113 of 113 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:45:56.214257Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T20:47:23.470655Z

Reference resolution

100 of 259 outbound references displayed

verified exact2
verified fuzzy0
unresolved98
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 14e03e25-324a-4605-8309-a22a8becd6bf · outbound

This paper cites Bloomberggpt: A large language model for finance,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Bloomberggpt: A large language model for finance,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.954673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 648cde59-fb59-449a-977f-34212e328b32 · outbound

This paper cites Making llms worth every penny: Resource-limited text classification in banking,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Making llms worth every penny: Resource-limited text classification in banking,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.964064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6d3ab1b-a11c-407e-b0d8-3df254591376 · outbound

This paper cites Better to ask in english: Cross-lingual evaluation of large language models for healthcare queries,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Better to ask in english: Cross-lingual evaluation of large language models for healthcare queries,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.968059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f508a8b-83cb-49ca-a856-709490adeff9 · outbound

This paper cites Non-intrusive and Unconstrained Keystroke Inference in VR Platforms via Infrared Side Channel.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Non-intrusive and Unconstrained Keystroke Inference in VR Platforms via Infrared Side Channel

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.971897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6ceddf4-3b99-452a-b397-e4160f92f56b · outbound

This paper cites Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.976229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec8f17c7-4d4a-495d-be3a-f289b38f0979 · outbound

This paper cites AutoLAW: Augmented Legal Reasoning through Legal Precedent Prediction.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations AutoLAW: Augmented Legal Reasoning through Legal Precedent Prediction

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.980439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9959c537-76ed-40ea-8098-75ebe3fa392a · outbound

This paper cites Badnets: Identifying vulnerabilities in the machine learning model supply chain,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Badnets: Identifying vulnerabilities in the machine learning model supply chain,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.984469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70b8d15-82d5-429f-ba5f-eb23c1320812 · outbound

This paper cites Sok: Security and privacy in machine learning,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Sok: Security and privacy in machine learning,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.992523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58db47f2-7d5b-4594-b8f1-058e1e66282b · outbound

This paper cites Talking about large language models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Talking about large language models,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T00:49:59.996922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 531fa963-2115-4289-97c9-1a493e630ad9 · outbound

This paper cites Attributing chatgpt-generated source codes,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Attributing chatgpt-generated source codes,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.000625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a83fe92-5a22-4f21-9a83-d0c1bec14fec · outbound

This paper cites Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.004307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3b8c47c-0eb3-41f8-afc3-52e764ed5517 · outbound

This paper cites SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.008277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5464dfd2-0b43-4c5d-b850-9766d2c0fa30 · outbound

This paper cites Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.012742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfc3c51d-4725-42c9-8b59-fa1a17535f84 · outbound

This paper cites I Can Find You in Seconds! Leveraging Large Language Models for Code Authorship Attribution.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations I Can Find You in Seconds! Leveraging Large Language Models for Code Authorship Attribution

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.017261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de871047-4680-476f-b2b1-6e88c7783c4f · outbound

This paper cites Visual instruction tuning,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Visual instruction tuning,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.022056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5929b4a0-d3fc-4db2-8a74-4b8f0c992e4c · outbound

This paper cites GPT-4 Technical Report.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations GPT-4 Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.026478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c53bd2c9-175f-4c61-a83d-bbc686ca2d9b · outbound

This paper cites Mistral 7b,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Mistral 7b,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.030907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6f5d9b4-d86e-46ba-ad7b-d5508d4866de · outbound

This paper cites Mixtral of experts,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Mixtral of experts,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.035150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afbc234a-0875-402c-9951-4a1835edc294 · outbound

This paper cites Language models are few-shot learners,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Language models are few-shot learners,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.039427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2877f053-7c77-4d66-9c2a-d900751be6eb · outbound

This paper cites Gpt-j-6b: A 6 billion pa- rameter autoregressive language model,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Gpt-j-6b: A 6 billion pa- rameter autoregressive language model,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.043756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7210239-c313-4595-a469-ecb353961de3 · outbound

This paper cites Language models are unsupervised multitask learners,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Language models are unsupervised multitask learners,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.047935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e40b050-9da0-46fe-a1aa-4c7faebbf1df · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations LLaMA: Open and Efficient Foundation Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.052158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e79261-e359-422d-80c1-846d995e6ebe · outbound

This paper cites Stanford alpaca: An instruction-following llama model,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Stanford alpaca: An instruction-following llama model,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.056448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7e31966-7c95-47bb-af9d-18d69e5a4cee · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.060655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29999a9f-abb1-44fc-8cb5-98badb5d0fee · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations TinyLlama: An Open-Source Small Language Model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.065244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04241166-3b14-46f4-86bc-199973adcb54 · outbound

This paper cites Qlora: Efficient finetuning of quantized llms,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Qlora: Efficient finetuning of quantized llms,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.069631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 414751f3-2f9c-4abf-9d17-a474c8e1033b · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Exploring the limits of transfer learning with a unified text-to-text transformer,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.073645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 400d61cd-3bcd-4d13-bdd6-dfcf8f0cf69e · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations The claude 3 model family: Opus, sonnet, haiku

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.077639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e490da16-3467-4332-9a04-e3ac80343eca · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations OPT: Open Pre-trained Transformer Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.081798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84fd1db6-34f7-4f91-9e88-8c93d2ba7cc0 · outbound

This paper cites PaLM 2 Technical Report.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations PaLM 2 Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.085956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 755ab855-60c3-4b42-b30d-a1e3b8bbf830 · outbound

This paper cites CodeBERT: A pre-trained model for programming and natural languages,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations CodeBERT: A pre-trained model for programming and natural languages,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.090717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cdc2359-157c-411c-a6dc-a7cb63568fd0 · outbound

This paper cites Graphcodebert: Pre-training code representations with data flow,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Graphcodebert: Pre-training code representations with data flow,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.094115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98706134-bd7f-4a4d-8975-984028586cd5 · outbound

This paper cites Unified pre-training for program understanding and gener- ation,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Unified pre-training for program understanding and gener- ation,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.097768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a0f8d6b-5436-49e3-99e1-ccc59d68da09 · outbound

This paper cites CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.101277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62be70f3-180e-41e4-a2e8-dbcb52e69c82 · outbound

This paper cites CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.104935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2db86a13-ad60-4aa7-9d2d-781395c73383 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Explaining and Harnessing Adversarial Examples

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.108918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb60e0e9-4e40-4fc0-aa6f-5399b5f968c7 · outbound

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

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.113001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26519f44-d22d-41b6-9d01-8d7186dbafb0 · outbound

This paper cites Query-based adversarial prompt generation,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Query-based adversarial prompt generation,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.116950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4633fcaa-b873-47e0-bc75-a1fd9a37d1a8 · outbound

This paper cites Autoprompt: Eliciting knowledge from language models with automatically generated prompts,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Autoprompt: Eliciting knowledge from language models with automatically generated prompts,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.125479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92d0f97e-dda9-4f88-ad7b-fab6b54827dc · outbound

This paper cites Gradient-Based Language Model Red Teaming.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Gradient-Based Language Model Red Teaming

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.133961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f253c677-8b13-4860-910e-a2b7832ad476 · outbound

This paper cites Transferring Backdoors between Large Language Models by Knowledge Distillation.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Transferring Backdoors between Large Language Models by Knowledge Distillation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.138261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3581b2e-3430-40ec-9317-875bcea40419 · outbound

This paper cites Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.142504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9045a3a6-0812-43d0-98d9-6b24dce36fc0 · outbound

This paper cites Badedit: Backdooring large language models by model editing,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Badedit: Backdooring large language models by model editing,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.146886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73974b64-3012-44fc-9c45-0b589fcdda11 · outbound

This paper cites Weight Poisoning Attacks on Pre-trained Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Weight Poisoning Attacks on Pre-trained Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.151000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd4dc227-b814-49e4-b117-aac35fc3d930 · outbound

This paper cites Megen: Generative backdoor in large language models via model editing,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Megen: Generative backdoor in large language models via model editing,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.155247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1629e101-42a7-482a-aff3-a659f89b85fb · outbound

This paper cites Backdoor attacks in federated learning by rare embeddings and gradient ensembling,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Backdoor attacks in federated learning by rare embeddings and gradient ensembling,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.163906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d94ed632-c46f-4d82-9844-972984ef8295 · outbound

This paper cites Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in nlp models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in nlp models,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.168018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 245dde42-59de-4d81-a8e9-68c700364084 · outbound

This paper cites Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.175831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c9060c4-a6e9-4929-9e5e-b568454fe136 · outbound

This paper cites NOTABLE: Transferable backdoor attacks against prompt-based NLP models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations NOTABLE: Transferable backdoor attacks against prompt-based NLP models,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.179549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d67f5933-14fd-4983-9f2f-b5e4a2fdf67f · outbound

This paper cites MEGen: Generative Backdoor into Large Language Models via Model Editing.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations MEGen: Generative Backdoor into Large Language Models via Model Editing

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.159324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 515c6212-d255-4288-80bf-910893381b32 · outbound

This paper cites Exploiting the vulnerability of large language models via defense-aware architectural backdoor,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Exploiting the vulnerability of large language models via defense-aware architectural backdoor,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.186816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39628013-5e5d-44c4-b37d-36e9adee60ce · outbound

This paper cites Red alarm for pre- trained models: Universal vulnerability to neuron-level backdoor attacks,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Red alarm for pre- trained models: Universal vulnerability to neuron-level backdoor attacks,

Reference 53

Resolution: verified exact; doi, observed 2026-08-09T00:50:01.109820Z

Source-reported events for the cited work

correction dated 2024-07-05. Source: crossref record 10.1007/s11633-024-1507-3->10.1007/s11633-022-1377-5:correction, observed 2026-07-11T03:01:46.04571+00:00. This notice travels one citation hop only.

Observation 9c7e0f5b-c4f9-45c2-b3a9-2f3f803c454f · outbound

This paper cites ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.201702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83034adc-5dc0-4b3d-a5d4-869e4ad0ff92 · outbound

This paper cites TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.205423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b61c8d2e-7324-4c11-a6ff-5eb74c068961 · outbound

This paper cites Blind Backdoors in Deep Learning Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Blind Backdoors in Deep Learning Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.183046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05ca18ab-94b5-4d08-bfef-9a4f6498259a · outbound

This paper cites An llm-assisted easy-to-trigger backdoor attack on code completion models: Injecting disguised vulnerabil- ities against strong detection,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations An llm-assisted easy-to-trigger backdoor attack on code completion models: Injecting disguised vulnerabil- ities against strong detection,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.212766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1c18849-4f35-4f9d-a784-a13df1db80f0 · outbound

This paper cites Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.190369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 170c79ac-7f82-4486-ad4c-89b073affd80 · outbound

This paper cites Hidden killer: Invisible textual backdoor attacks with syntactic trigger,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Hidden killer: Invisible textual backdoor attacks with syntactic trigger,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.220575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2842de62-eb3f-4b82-aeda-57679d81b463 · outbound

This paper cites Synghost: Imperceptible and universal task- agnostic backdoor attack in pre-trained language models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Synghost: Imperceptible and universal task- agnostic backdoor attack in pre-trained language models,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.224940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7474fb2-1479-4d30-a504-c367d1caf0bf · outbound

This paper cites Punctuation matters! stealthy backdoor attack for language models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Punctuation matters! stealthy backdoor attack for language models,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.233337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51f01e95-385d-482b-aa9f-0ebd28a66ef1 · outbound

This paper cites Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.241502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 531821ff-8b0c-4e6e-99bb-0d5304288326 · outbound

This paper cites Large language models are better adversaries: Exploring generative clean- label backdoor attacks against text classifiers,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Large language models are better adversaries: Exploring generative clean- label backdoor attacks against text classifiers,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.209196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1164764b-0ad3-4638-94a9-c0237ce8837c · outbound

This paper cites The Philosopher's Stone: Trojaning Plugins of Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations The Philosopher's Stone: Trojaning Plugins of Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.249934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1a77d20-191f-46d8-bcb1-3ba1d7395651 · outbound

This paper cites Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.216333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c97420-5148-47c1-b6e5-346ae199e0a3 · outbound

This paper cites Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.258528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8d483d-be58-4304-b046-001b526e4e8c · outbound

This paper cites Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.263045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b392f18b-06b6-4fbd-a3f2-18e831acd521 · outbound

This paper cites SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.228880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66ef195a-29f4-4328-9ea4-136903eb4440 · outbound

This paper cites LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.271550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c997404-1a5d-4d84-aff5-1c601030ed93 · outbound

This paper cites Punctuation Matters! Stealthy Backdoor Attack for Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Punctuation Matters! Stealthy Backdoor Attack for Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.237375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae5a2a4-b3ba-45f3-a634-5d476c74c974 · outbound

This paper cites Backdooring instruction- tuned large language models with virtual prompt injection,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Backdooring instruction- tuned large language models with virtual prompt injection,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.282682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a9a2616-15b3-4bc1-a554-9f3471caa7fd · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations LoRA: Low-Rank Adaptation of Large Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.245794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a428428e-f539-4550-8dc9-ec4b911e79ae · outbound

This paper cites On the exploitability of instruction tuning,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations On the exploitability of instruction tuning,

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.290332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d59c889-f305-49c7-9502-9baa8364efc9 · outbound

This paper cites A gradient control method for backdoor attacks on parameter- efficient tuning,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations A gradient control method for backdoor attacks on parameter- efficient tuning,

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.254194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85df0325-872b-491a-b561-afe89d986e2a · outbound

This paper cites Vl-trojan: Multimodal instruction backdoor attacks against autoregressive visual language models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Vl-trojan: Multimodal instruction backdoor attacks against autoregressive visual language models,

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.301434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5929241-a237-4646-9d60-01801ffcd8be · outbound

This paper cites Poisoning language models during instruction tuning,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Poisoning language models during instruction tuning,

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.309003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de7be2f5-6984-44a4-9b89-035e0cde70ec · outbound

This paper cites Turning Generative Models Degenerate: The Power of Data Poisoning Attacks.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Turning Generative Models Degenerate: The Power of Data Poisoning Attacks

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.267302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f222305c-a255-4a26-beed-de554fa8cfaa · outbound

This paper cites SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning

Reference 78

Resolution: verified exact; local_arxiv, observed 2026-08-09T00:50:02.708912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dd68f3ae-c91a-40f4-812e-a74e0e1079b4 · outbound

This paper cites Composite backdoor attacks against large language models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Composite backdoor attacks against large language models,

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.275784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8d13de4-9f76-4f16-8a85-16214740f799 · outbound

This paper cites Neurotoxin: Durable Backdoors in Federated Learning.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Neurotoxin: Durable Backdoors in Federated Learning

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.325647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f0edddf-b376-4fff-af26-85fac3e7f5d7 · outbound

This paper cites Badmerging: Backdoor attacks against model merging,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Badmerging: Backdoor attacks against model merging,

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.329957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 275e3fdb-5a3a-48e3-8ff7-f0998800db91 · outbound

This paper cites Learning to Poison Large Language Models for Downstream Manipulation.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Learning to Poison Large Language Models for Downstream Manipulation

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.286273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e83e4e07-1343-437c-a862-a3dee481106b · outbound

This paper cites PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.342772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2f9759f-c822-489a-ab22-46df4cd0806d · outbound

This paper cites On the Exploitability of Instruction Tuning.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations On the Exploitability of Instruction Tuning

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.293834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2409fb2-aebe-4140-90dd-9b3b51ea3946 · outbound

This paper cites Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.297603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5709a7b-efc5-4135-95e0-4d89c356e0c0 · outbound

This paper cites Prompt as triggers for backdoor attack: Examining the vulnerability in language models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Prompt as triggers for backdoor attack: Examining the vulnerability in language models,

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.360425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59878673-9152-4343-b80b-cb4ef971216e · outbound

This paper cites VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.305089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c811234-8bb3-4334-b2ed-bd9dbd1a3504 · outbound

This paper cites Rlhfpoison: Reward poisoning attack for reinforcement learning with human feedback in large language models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Rlhfpoison: Reward poisoning attack for reinforcement learning with human feedback in large language models,

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.369209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de33045c-aac9-4d96-98f0-85c33151cf56 · outbound

This paper cites Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.312809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b91c2c9-b116-465c-80a1-abf66d2bc7a7 · outbound

This paper cites BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.382122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 433e8a0a-e080-43f3-a453-1f1df46206b3 · outbound

This paper cites Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.321494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4945f781-4b3c-4545-af78-7f575e997b8c · outbound

This paper cites Badagent: Inserting and activating backdoor attacks in llm agents,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Badagent: Inserting and activating backdoor attacks in llm agents,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.391009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a3a75ba-419e-4250-81a7-3bb3242874e9 · outbound

This paper cites Adaptivebackdoor: Backdoored language model agents that detect human overseers,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Adaptivebackdoor: Backdoored language model agents that detect human overseers,

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.398918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc0dc19d-d03b-4d95-9ac7-9f66abf39f54 · outbound

This paper cites BadMerging: Backdoor Attacks Against Model Merging.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations BadMerging: Backdoor Attacks Against Model Merging

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.334060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510f2720-1814-4ed7-9c4c-7c4fe7354e63 · outbound

This paper cites Ppt: Backdoor attacks on pre-trained models via poisoned prompt tuning,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Ppt: Backdoor attacks on pre-trained models via poisoned prompt tuning,

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.338493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10781369-72d7-4515-8178-1a62af2f5764 · outbound

This paper cites Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.410625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9eac4a1-4a0d-430f-a69a-6e0830a5d518 · outbound

This paper cites Exploring the universal vulnerability of prompt-based learning paradigm,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Exploring the universal vulnerability of prompt-based learning paradigm,

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.347028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb6ef1ff-1af3-45fc-bbb0-829f3618cdf8 · outbound

This paper cites Alanca: Active learning guided adversarial attacks for code comprehension on diverse pre- trained and large language models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Alanca: Active learning guided adversarial attacks for code comprehension on diverse pre- trained and large language models,

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.418910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37248f74-aed0-47cb-bc41-4e17a52a4771 · outbound

This paper cites BadPrompt: Backdoor Attacks on Continuous Prompts.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations BadPrompt: Backdoor Attacks on Continuous Prompts

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.355867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5adc3c9-abcb-45ab-a50c-3adf95623c95 · outbound

This paper cites Multi- target backdoor attacks for code pre-trained models,.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Multi- target backdoor attacks for code pre-trained models,

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.427377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 800c2181-654a-4592-b3d5-fa4f73d67cc3 · outbound

This paper cites Universal Jailbreak Backdoors from Poisoned Human Feedback.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.364674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c83337f1-0912-470d-84b6-9313d3743c0e · inbound

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation cites this paper.

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T05:45:56.214257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d51b139-481e-43b1-bf9d-9c91d0e3fa7d · inbound

Pruning Strategies for Backdoor Defense in LLMs cites this paper.

Pruning Strategies for Backdoor Defense in LLMs A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T15:19:14.965446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12eee93d-7aeb-4fa5-addd-3020c7601348 · inbound

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents cites this paper.

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T21:44:12.472875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfea1b3b-ab44-4949-9f0f-707cb3c8080f · inbound

Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts cites this paper.

Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-18T04:25:52.134980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5a42b2e2-d79c-40e1-956c-0293916a241c · inbound

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward cites this paper.

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:10:59.762851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 583e2a0e-2db4-422f-826a-82d121958c9b · inbound

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers cites this paper.

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:31:07.703958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 779c12db-b5e6-46ae-9e52-74d19fd79998 · inbound

On the Privacy of LLMs: An Ablation Study cites this paper.

On the Privacy of LLMs: An Ablation Study A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:25:48.866703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6171557c-7e8b-4e1b-b9b5-3cda0f24f630 · inbound

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs cites this paper.

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:47:23.472235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation caadd94a-9aac-4ef2-8459-c658acfce8cb · inbound

Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors cites this paper.

Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 65

Resolution: malformed identifier; arxiv_id, observed 2026-06-30T08:04:28.746072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7b47a274-c1bd-43bc-9e01-d7e2b50e540e · inbound

Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors cites this paper.

Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 63

Resolution: malformed identifier; no resolver link, observed 2026-08-04T04:39:06.950528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b16460d-6c13-4811-b94e-1d81ebeda072 · inbound

Toward a Unified Security and Privacy Framework for AI-Native 6G Networks cites this paper.

Toward a Unified Security and Privacy Framework for AI-Native 6G Networks A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 135

Resolution: verified exact; arxiv_id, observed 2026-07-02T10:26:51.394825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ec30df92-7a97-4f3c-9842-8833e8b5b87e · inbound

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests cites this paper.

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T09:30:49.265611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2d0e15f-2955-4bfc-9f2f-6d1db8455ab8 · inbound

Hiding in Plain Sight: An Effective Physical Adversarial Patch Attack against Visual-Infrared Fused Face Detection cites this paper.

Hiding in Plain Sight: An Effective Physical Adversarial Patch Attack against Visual-Infrared Fused Face Detection A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 105

Resolution: unresolved; no resolver link, observed 2026-07-31T23:55:34.674415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.