Paper Citation Record · LEDGER

Neutralizing Backdoors through Information Conflicts for Large Language Models

As of 13 August 2026, this Paper Citation Record lists 82 of 82 outbound references and 3 inbound Pith citation observations for arXiv:2411.18280.

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

pith.paper-citation-record.v1
2411.18280 v1

Coverage vector

measured 82 of 82 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T11:25:32.023656Z

measured 85 of 85 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:24:30.476290Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T20:32:04.740012Z

Reference resolution

82 of 82 outbound references displayed

verified exact1
verified fuzzy32
unresolved48
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cb0674ff-6e46-4cfd-84d9-3ab184341727 · outbound

This paper cites LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements.

Neutralizing Backdoors through Information Conflicts for Large Language Models LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.602989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a047dc4-ce5a-4098-ab5b-ac84c4a66e5f · outbound

This paper cites Towards stealthy backdoor attacks against speech recognition via elements of sound.

Neutralizing Backdoors through Information Conflicts for Large Language Models Towards stealthy backdoor attacks against speech recognition via elements of sound

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.715870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7589b42f-be3b-4e96-881d-a40215545385 · outbound

This paper cites Badprompt: Backdoor attacks on continuous prompts.

Neutralizing Backdoors through Information Conflicts for Large Language Models Badprompt: Backdoor attacks on continuous prompts

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.720156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2b896b6-e564-411f-ac3a-c9d7323db008 · outbound

This paper cites Backdoor attacks and defenses for deep neural networks in outsourced cloud environments.

Neutralizing Backdoors through Information Conflicts for Large Language Models Backdoor attacks and defenses for deep neural networks in outsourced cloud environments

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.724716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 420e154c-6827-42b1-9e4c-7f186849291b · outbound

This paper cites Deep reinforcement learning from human preferences.

Neutralizing Backdoors through Information Conflicts for Large Language Models Deep reinforcement learning from human preferences

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.729614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 567f79f8-5ec7-4561-bb60-74a454622479 · outbound

This paper cites Triggerless Backdoor Attack for NLP Tasks with Clean Labels.

Neutralizing Backdoors through Information Conflicts for Large Language Models Triggerless Backdoor Attack for NLP Tasks with Clean Labels

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.733560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06db0671-0c72-406e-8cc5-c05f2eeb4cb2 · outbound

This paper cites Arcee's MergeKit: A Toolkit for Merging Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Arcee's MergeKit: A Toolkit for Merging Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.738281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0647061-67e6-4b24-ae4d-4c7ca155787f · outbound

This paper cites Atteq- nn: Attention-based qoe-aware evasive backdoor attacks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Atteq- nn: Attention-based qoe-aware evasive backdoor attacks

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:33.067462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 59eb5a7b-f180-472b-aafb-1ed4c82ed17c · outbound

This paper cites Defense-resistant backdoor at- tacks against deep neural networks in outsourced cloud environment.

Neutralizing Backdoors through Information Conflicts for Large Language Models Defense-resistant backdoor at- tacks against deep neural networks in outsourced cloud environment

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:33.055306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ffe75be8-b1b9-416f-ad59-4e8412a31237 · outbound

This paper cites Redeem myself: Purifying back- doors in deep learning models using self attention distillation.

Neutralizing Backdoors through Information Conflicts for Large Language Models Redeem myself: Purifying back- doors in deep learning models using self attention distillation

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:33.043038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d1808e2a-406b-4105-a28b-df642321c0ae · outbound

This paper cites Palette: Physically-realizable backdoor attacks against video recognition models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Palette: Physically-realizable backdoor attacks against video recognition models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:33.031264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ac494351-aa6c-426e-98f5-a8e12015de78 · outbound

This paper cites Exploring Backdoor Vulnerabilities of Chat Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Exploring Backdoor Vulnerabilities of Chat Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.758683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b00b7f88-4582-4804-a221-28912fde4779 · outbound

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

Neutralizing Backdoors through Information Conflicts for Large Language Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.763613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 822fde64-ea24-472d-a746-fb8a60c856b8 · outbound

This paper cites Composite Backdoor Attacks Against Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Composite Backdoor Attacks Against Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.767450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e615a840-db0c-4d91-ae40-5db4d5837cea · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Neutralizing Backdoors through Information Conflicts for Large Language Models Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.770839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e03ff390-c910-4c8a-a8bd-e04497729101 · outbound

This paper cites Editing Models with Task Arithmetic.

Neutralizing Backdoors through Information Conflicts for Large Language Models Editing Models with Task Arithmetic

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.774376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 122e5b0b-a68d-4800-88b5-f5a081a6abf3 · outbound

This paper cites Model-reuse attacks on deep learning systems.

Neutralizing Backdoors through Information Conflicts for Large Language Models Model-reuse attacks on deep learning systems

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:33.017144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7d655ecf-9972-4d3e-8c02-0b21adbc3117 · outbound

This paper cites Backdoor attacks against learning systems.

Neutralizing Backdoors through Information Conflicts for Large Language Models Backdoor attacks against learning systems

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.781129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96fe5b8-da66-44e6-a456-84c0163b8fa5 · outbound

This paper cites Chatgpt for good? On opportunities and challenges of large language models for education.

Neutralizing Backdoors through Information Conflicts for Large Language Models Chatgpt for good? On opportunities and challenges of large language models for education

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.996875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0a46bc26-72b7-4500-8f9a-bfe24e8f1979 · outbound

This paper cites Textual backdoor attack for the text classification system.

Neutralizing Backdoors through Information Conflicts for Large Language Models Textual backdoor attack for the text classification system

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.984067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f0922503-6277-4e7a-8c99-dd9ff70c5a4e · outbound

This paper cites Fast inference from transformers via speculative decoding.

Neutralizing Backdoors through Information Conflicts for Large Language Models Fast inference from transformers via speculative decoding

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.971542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dba8c6d9-a6d2-462f-9b68-38fc751fdea4 · outbound

This paper cites Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.794884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ea7470e-95fe-4159-85dc-91d73704e64d · outbound

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

Neutralizing Backdoors through Information Conflicts for Large Language Models Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.798794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98cf3539-0236-4753-bd3e-ffd4d011d18f · outbound

This paper cites Chain- of-scrutiny: Detecting backdoor attacks for large language models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Chain- of-scrutiny: Detecting backdoor attacks for large language models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.802721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b81a080-d614-4825-8d0b-482e68e2f5ed · outbound

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

Neutralizing Backdoors through Information Conflicts for Large Language Models BadEdit: Backdooring large language models by model editing

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.806553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f89a63e3-32a8-477d-9ddd-48c55ed2c1e6 · outbound

This paper cites Multi-target Backdoor Attacks for Code Pre-trained Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Multi-target Backdoor Attacks for Code Pre-trained Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.810305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6cbb5af-4ac9-4746-b982-adee26ecd11b · outbound

This paper cites Neural attention distillation: Erasing backdoor triggers from deep neural networks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Neural attention distillation: Erasing backdoor triggers from deep neural networks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.814198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64c6903c-033b-440b-8992-7a8cc5ca09d2 · outbound

This paper cites Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.817782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae2f896f-5e55-4068-931b-07461e45eff8 · outbound

This paper cites Rethinking the Trigger of Backdoor Attack.

Neutralizing Backdoors through Information Conflicts for Large Language Models Rethinking the Trigger of Backdoor Attack

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.821516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11159c6e-aefe-4eb8-a3e3-d01867c06591 · outbound

This paper cites CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.825411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbe87eda-653d-4856-a38f-027cbd379473 · outbound

This paper cites Unveiling the Pitfalls of Knowledge Editing for Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Unveiling the Pitfalls of Knowledge Editing for Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.829209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e9242c-14c0-47e2-93d1-3872ce1394b4 · outbound

This paper cites Composite backdoor attack for deep neural network by mixing existing benign features.

Neutralizing Backdoors through Information Conflicts for Large Language Models Composite backdoor attack for deep neural network by mixing existing benign features

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.951917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 03b98c03-cc34-4c47-b980-62a0e08192ba · outbound

This paper cites Fine-pruning: Defending against backdooring attacks on deep neural networks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Fine-pruning: Defending against backdooring attacks on deep neural networks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.836786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc73ad7b-cef3-4a96-9775-b8bcd0602b16 · outbound

This paper cites Oppor- tunistic backdoor attacks: Exploring human-imperceptible vulnerabil- ities on speech recognition systems.

Neutralizing Backdoors through Information Conflicts for Large Language Models Oppor- tunistic backdoor attacks: Exploring human-imperceptible vulnerabil- ities on speech recognition systems

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.931350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a5588800-d98c-4439-bdf8-096acdc63121 · outbound

This paper cites Trojaning attack on neural networks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Trojaning attack on neural networks

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.917866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 06c1b231-9583-422a-9235-fb28bf1851a1 · outbound

This paper cites Practical backdoor attack against speaker recognition system.

Neutralizing Backdoors through Information Conflicts for Large Language Models Practical backdoor attack against speaker recognition system

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.904618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8bc59306-abd7-4a5b-9e47-0f31f8e2fdef · outbound

This paper cites Locating and editing factual associations in gpt.

Neutralizing Backdoors through Information Conflicts for Large Language Models Locating and editing factual associations in gpt

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.849848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa8dfa28-5566-4a18-820e-71ae7878e1a9 · outbound

This paper cites Mass-Editing Memory in a Transformer.

Neutralizing Backdoors through Information Conflicts for Large Language Models Mass-Editing Memory in a Transformer

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.853369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7240ef11-81d9-4756-b7a3-2c89c03a709f · outbound

This paper cites Textrank: Bringing order into text.

Neutralizing Backdoors through Information Conflicts for Large Language Models Textrank: Bringing order into text

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.884143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 91337975-2812-4709-a5b3-be5f43af3374 · outbound

This paper cites Training language models to follow in- structions with human feedback.

Neutralizing Backdoors through Information Conflicts for Large Language Models Training language models to follow in- structions with human feedback

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.872525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e811145f-096c-4685-8823-20f7bae94005 · outbound

This paper cites Hidden trigger backdoor attack on NLP models via linguistic style manipulation.

Neutralizing Backdoors through Information Conflicts for Large Language Models Hidden trigger backdoor attack on NLP models via linguistic style manipulation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.857460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4716844b-a90b-4edb-a987-0f8a4b1ff7a3 · outbound

This paper cites ONION: A Simple and Effective Defense Against Textual Backdoor Attacks.

Neutralizing Backdoors through Information Conflicts for Large Language Models ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.866664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd7ae26f-e406-410a-b3d9-b6d9d6b9e159 · outbound

This paper cites Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger.

Neutralizing Backdoors through Information Conflicts for Large Language Models Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.870461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26904e98-9ff1-49b1-97bf-2a24116dd2b7 · outbound

This paper cites Towards a proactive ML approach for detecting backdoor poison samples.

Neutralizing Backdoors through Information Conflicts for Large Language Models Towards a proactive ML approach for detecting backdoor poison samples

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.844028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 98a05522-fb2b-48ef-a822-ef0518a3d723 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Neutralizing Backdoors through Information Conflicts for Large Language Models Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.877735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd1df4b-41f2-4880-9607-baba2d61b7bf · outbound

This paper cites Language models are unsupervised multitask learners.

Neutralizing Backdoors through Information Conflicts for Large Language Models Language models are unsupervised multitask learners

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.881642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12bbfee7-4da5-43dd-bd6c-a260137e1bec · outbound

This paper cites Identifying physically realizable triggers for backdoored face recognition networks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Identifying physically realizable triggers for backdoored face recognition networks

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.823038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 23a351e2-35ba-4ee4-935f-c7f63c54698e · outbound

This paper cites Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs.

Neutralizing Backdoors through Information Conflicts for Large Language Models Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.889053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a72722c5-2769-4bc5-b71e-27b6d21ee2da · outbound

This paper cites Hidden trigger backdoor attacks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Hidden trigger backdoor attacks

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.812334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 78bc8c9b-0fdd-41c5-ac64-0020a83182b8 · outbound

This paper cites Dynamic Backdoor Attacks Against Machine Learning Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Dynamic Backdoor Attacks Against Machine Learning Models

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-12T11:25:32.247340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2978ded2-99fe-45cc-a060-ecf35c0c0419 · outbound

This paper cites Carer: Contextualized affect representations for emotion recognition.

Neutralizing Backdoors through Information Conflicts for Large Language Models Carer: Contextualized affect representations for emotion recognition

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.800507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ff60b46c-2464-442c-a637-69e4ef474dd1 · outbound

This paper cites You autocomplete me: Poisoning vulnerabilities in neural code com- pletion.

Neutralizing Backdoors through Information Conflicts for Large Language Models You autocomplete me: Poisoning vulnerabilities in neural code com- pletion

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.788190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9b6469a9-5747-4169-addd-04df24cdc263 · outbound

This paper cites On the exploitability of instruction tun- ing.

Neutralizing Backdoors through Information Conflicts for Large Language Models On the exploitability of instruction tun- ing

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.777242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e2f5f383-ae81-4bc1-94db-222522b02e07 · outbound

This paper cites Recursive deep models for semantic compositionality over a sentiment treebank.

Neutralizing Backdoors through Information Conflicts for Large Language Models Recursive deep models for semantic compositionality over a sentiment treebank

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.764883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6d675dd7-8b20-4b8b-8683-51768177fff1 · outbound

This paper cites Natural Backdoor Attack on Text Data.

Neutralizing Backdoors through Information Conflicts for Large Language Models Natural Backdoor Attack on Text Data

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.918495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09239ed1-fd0a-4e69-8a46-2c804302edba · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models A Simple and Effective Pruning Approach for Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.922243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd1a3044-1374-40c4-8419-52e737835df6 · outbound

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

Neutralizing Backdoors through Information Conflicts for Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.926402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7778ed53-eb85-4ebb-b2ba-1f5ea2a2d0aa · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.930248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3227093e-3ba5-47b9-9b16-c6f253eb807f · outbound

This paper cites Neural cleanse: Identi- fying and mitigating backdoor attacks in neural networks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Neural cleanse: Identi- fying and mitigating backdoor attacks in neural networks

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.751965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6c45ac88-9af8-4ad9-96ac-c158d3a47b77 · outbound

This paper cites Adversarial Demonstration Attacks on Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Adversarial Demonstration Attacks on Large Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.937914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c8ab148-d042-475a-b422-ba73e8afde0b · outbound

This paper cites Backdoor attacks against transfer learning with pre-trained deep learning models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Backdoor attacks against transfer learning with pre-trained deep learning models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.740652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2141d306-227e-4fa3-bd89-ce8bde5d13ea · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Neutralizing Backdoors through Information Conflicts for Large Language Models Finetuned Language Models Are Zero-Shot Learners

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.944984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ef47f0b-c9fe-4119-a86d-1e152c797446 · outbound

This paper cites Emergent Abilities of Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Emergent Abilities of Large Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.948884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cbe41ce-5686-41dc-81e8-e65498a877a1 · outbound

This paper cites Bd- mmt: Backdoor sample detection for language models through model mutation testing.

Neutralizing Backdoors through Information Conflicts for Large Language Models Bd- mmt: Backdoor sample detection for language models through model mutation testing

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.729291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d0c7dae4-14bd-473d-910f-49583df96545 · outbound

This paper cites Model soups: Averaging weights of multiple fine-tuned models improves ac- curacy without increasing inference time.

Neutralizing Backdoors through Information Conflicts for Large Language Models Model soups: Averaging weights of multiple fine-tuned models improves ac- curacy without increasing inference time

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.718270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7587af65-0d90-4f6f-8799-109cc84c929c · outbound

This paper cites Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts.

Neutralizing Backdoors through Information Conflicts for Large Language Models Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.960699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1580311-05c6-432f-8b3a-68cef95717f0 · outbound

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

Neutralizing Backdoors through Information Conflicts for Large Language Models Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.964368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 776fb0dc-cb5e-4e32-829d-93fdba0be02d · outbound

This paper cites Trojllm: A black-box trojan prompt attack on large language models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Trojllm: A black-box trojan prompt attack on large language models

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.706264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation afa44701-0f6a-43aa-8a7c-719dab8802c2 · outbound

This paper cites TIES-merging: Resolving interference when merging models.

Neutralizing Backdoors through Information Conflicts for Large Language Models TIES-merging: Resolving interference when merging models

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.694242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3285b160-5fec-4c8c-8df9-f6358ce45f95 · outbound

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

Neutralizing Backdoors through Information Conflicts for Large Language Models Backdooring instruction-tuned large language models with virtual prompt injection

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.681343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6ce008a6-67bc-4f57-b9bc-94a29f65a8d4 · outbound

This paper cites A comprehensive overview of backdoor attacks in large language models within communication networks.

Neutralizing Backdoors through Information Conflicts for Large Language Models A comprehensive overview of backdoor attacks in large language models within communication networks

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.978647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53824f08-2337-4e71-8e59-72ae79a05971 · outbound

This paper cites Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.982926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afb8afcf-d412-46d6-91c7-d14044e6b4ab · outbound

This paper cites RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.986973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5833c6f-1985-4133-ab77-2cb6cb202444 · outbound

This paper cites Poisonprompt: Backdoor attack on prompt-based large language models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Poisonprompt: Backdoor attack on prompt-based large language models

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.660363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f7b035a0-66f9-4226-ad8f-d254a048dfec · outbound

This paper cites Latent backdoor attacks on deep neural networks.

Neutralizing Backdoors through Information Conflicts for Large Language Models Latent backdoor attacks on deep neural networks

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.646776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation da08f7d8-802e-4b54-ad50-53fe151022d8 · outbound

This paper cites BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:31.998778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 010bb81d-a2cb-4470-b384-d8b380cbae44 · outbound

This paper cites Composing parameter- efficient modules with arithmetic operation.

Neutralizing Backdoors through Information Conflicts for Large Language Models Composing parameter- efficient modules with arithmetic operation

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:25:32.633235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 032f5686-5aa0-4cc7-99df-b6fbb46f5b87 · outbound

This paper cites Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:32.007402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dbf6ecb-805c-4ddf-b7a4-01f83f182060 · outbound

This paper cites Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning.

Neutralizing Backdoors through Information Conflicts for Large Language Models Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:32.011136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e84309ec-a076-4131-b39f-e964a9566f49 · outbound

This paper cites Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:32.015117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3acd0b42-bab0-471d-abc3-b69b35d0b8d6 · outbound

This paper cites A Survey of Large Language Models.

Neutralizing Backdoors through Information Conflicts for Large Language Models A Survey of Large Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-12T11:25:32.019298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79da5425-bc65-4b79-92a8-d1e2be2a7dbc · outbound

This paper cites I MPACT OF DIFFERENT MODEL MERGING METHODS.

Neutralizing Backdoors through Information Conflicts for Large Language Models I MPACT OF DIFFERENT MODEL MERGING METHODS

Reference 82

Resolution: malformed identifier; raw_fallback, observed 2026-08-12T11:25:32.618426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

Observation 54dff87c-639a-4984-b2ab-b6dd5dd8e5d7 · inbound

Defending against Backdoor Attacks via Module Switching cites this paper.

Defending against Backdoor Attacks via Module Switching Neutralizing Backdoors through Information Conflicts for Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-22T20:32:04.741912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 084f9e84-66bf-4c39-85db-ab23fe4137f8 · inbound

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques cites this paper.

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques Neutralizing Backdoors through Information Conflicts for Large Language Models

Reference 179

Resolution: unresolved; no resolver link, observed 2026-08-06T16:24:30.476290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 109b2d8f-9d3a-40d2-b0d5-751942213e88 · inbound

BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models cites this paper.

BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models Neutralizing Backdoors through Information Conflicts for Large Language Models

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:02:58.913067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.