Pith. sign in

Paper Citation Record · LEDGER

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

As of 8 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 2 inbound Pith citation observations for arXiv:2505.23561.

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

pith.paper-citation-record.v1
2505.23561 v1

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:48:18.371254Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:05:10.309553Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T11:38:05.615659Z

Reference resolution

50 of 50 outbound references displayed

  • verified exact2
  • verified fuzzy0
  • unresolved48
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7f0d3e58-9117-4832-aaf3-a44fbb47e16a · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:22.602217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:13.693978Z digest=sha256:59daeb10d5987b3d4eabe6efa58c07e60974e4f458ce7eb5a04d4e969b5fc480

Observation 6c4d0816-2c71-469b-bb88-a39f1fa50420 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:22.432778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:13.800757Z digest=sha256:317880da90ad0415fadf72c253703405e90a8497307f44ff9501ebeef17feee2

Observation 2e46fb92-cefd-48cc-8bfd-7d876c7b60af · outbound

This paper cites Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:13.899297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:13.899297Z digest=sha256:42d3d7bb0a4eef01135bba77a2f430493313d1e137dac18d228662157d7058d5

Observation 4c8b477c-832f-41a1-8450-47c8e09715fd · outbound

This paper cites Qwen Technical Report.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Qwen Technical Report

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:13.986300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:13.986300Z digest=sha256:2cd4ffd1f55631209b318f1f78a5f083a817b06bb6be4beeb499d69bd8272c4c

Observation 6acf0a50-fd6e-4657-b3af-d64b733adaa9 · outbound

This paper cites BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:14.057301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:14.057301Z digest=sha256:d13de6b7d2eab64b7dbc9abb1f0aa2f731cd38bbaabf4e708121b676170dc483

Observation 122aca9f-7cbc-436a-a84d-7f5432689998 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Training Verifiers to Solve Math Word Problems

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:14.163455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:14.163455Z digest=sha256:01ae00d21db4b49a79663293c82e87d435549a993eeb53efa9cdc47afe1e0d2f

Observation 797edc12-481f-4f6d-ad2f-9df398226fc8 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:22.273813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:14.242518Z digest=sha256:c0f3e6a49f335dca2957f3977aaa137479218888e5efac728db97a02f94c96de

Observation c8b8ca49-82e1-44e6-96e1-bcd6d9cfcfbc · outbound

This paper cites DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:14.350555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:14.350555Z digest=sha256:9ed9d9d1058bcb9db98d6bb7353467dc37e2320b1fe6978ca3dc620b0fa8dde6

Observation 70c6f83e-680c-4fee-a741-650da0bf8f12 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:22.040158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:14.461049Z digest=sha256:dd905795cff8a7c7e43d374f472c305ae4cf6b8877f81fe64d5717b4a053492d

Observation 83e96470-e45e-45ac-9790-37df9915383d · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 10

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:21.827998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:14.525259Z digest=sha256:91046a6753ef5973cb2540347a945b6ad9f877a9f51c59f9ba4f131b46078898

Observation 60284a90-ff1a-485d-a879-a944b35ab9cb · outbound

This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:14.631580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:14.631580Z digest=sha256:2acdc3b8179778397653c43702684cc103b0caf7f80142eaed58ee7c4de0ef4f

Observation b3c169b7-3ea2-4a6c-96b8-fb5787742296 · outbound

This paper cites SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:14.724774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:14.724774Z digest=sha256:9ccfa4c1c0e7af8a93d5199b23068814b542be2fcebde2724cbd486cb5c45fbc

Observation 7bab8c33-e09a-4ba8-a0fb-3c811ac4d076 · outbound

This paper cites Composite Backdoor Attacks Against Large Language Models.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Composite Backdoor Attacks Against Large Language Models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:14.815514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:14.815514Z digest=sha256:465662c02bf950afe98cae07fafe6d6c87a5d7525d365066d0f4502718291809

Observation 79c1b52f-28ef-4ebe-b102-724fe08128d2 · outbound

This paper cites Lawyer LLaMA Technical Report.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Lawyer LLaMA Technical Report

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:14.903159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:14.903159Z digest=sha256:b8d4cea0a1f429c6f4404aa5c013a30a626cd3e90b99d2928131eed17a812cb3

Observation 36ccc6a4-8b7a-4f57-9820-8c94decb7d5b · outbound

This paper cites Editing Models with Task Arithmetic.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Editing Models with Task Arithmetic

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:14.987844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:14.987844Z digest=sha256:7fd4071acacf495fc1ed7989b0f246376316b9ab172954fabc3ecd645a0f577f

Observation 8fd8d335-7d11-454b-8c7b-c03785fead1b · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:15.086856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:15.086856Z digest=sha256:16b7df95f27e56f893da6e920f696e6a932a0f9dd651922d056876273c2aef6b

Observation 83528510-2044-476a-aa85-25eeaebd8dea · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 17

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:21.472996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:15.178603Z digest=sha256:202ae7ffab7db7d5be50bf214f447e7ba6b7f7889d95bbed39ce3d79b78a6c42

Observation 450d7339-62b7-46c8-a576-d70a1c294c73 · outbound

This paper cites Mistral 7B.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Mistral 7B

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:15.244085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:15.244085Z digest=sha256:81545372806453702a6786cc9cbb52a06f3816b13f11ace36b2600a51d171aa8

Observation 912b481f-c6ec-4061-95b4-ef63f4ff0f8c · outbound

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

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:15.362800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:15.362800Z digest=sha256:e66c3c3a4c6e63a03d83b589f7e506ada74a8c1e47832d550c4d3f9fc63c4d5e

Observation 32040036-1434-4e38-8918-f5dd16937f89 · outbound

This paper cites Competition-Level Code Generation with AlphaCode.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Competition-Level Code Generation with AlphaCode

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:15.436062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:15.436062Z digest=sha256:017d9fd1774b01834989862e8989d8a7ee70a68bec2b8ce6df84da2fd979ce22

Observation 9183bd86-2785-44ee-a794-60d21b3f351b · outbound

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

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:15.563187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:15.563187Z digest=sha256:4d93cbe0af27c775e4939005e054efc5d725ad8d113502b80fdcbfeb62182dc0

Observation 4276fcd2-08a7-4e5a-869f-48d675dbf236 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:21.174769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:15.621816Z digest=sha256:02ac7cfb6a09bef98ebbb6d34648a2a33332a8d7c01cb270980a35a519fdaebc

Observation c1b6bdf9-bdf5-4b8f-a228-b64a77d1812e · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:20.938528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:15.715639Z digest=sha256:3993c010a2ecbe1098f63c094a4e6c02c3db387a634b9816631d523d9c71a8a4

Observation 15c53ae5-6c1d-4a3c-adfe-4dd50ec74692 · outbound

This paper cites Improving Large Language Model Fine-tuning for Solving Math Problems.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Improving Large Language Model Fine-tuning for Solving Math Problems

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:15.805007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:15.805007Z digest=sha256:7c418355f2e41d60e9938e104c340cc808195b9f7d0f1330841cb112328abcd0

Observation cbec3f81-1507-4073-b573-03260797374c · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 25

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:20.718390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:15.891571Z digest=sha256:cb3dbb9dfc5b4b49906dc3c1cad49f3d0d7862e3f51f1bb916bd33bdbd65aba2

Observation 0a5def35-8596-4b5b-a987-b8b146215fd2 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 26

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:20.534988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:15.965811Z digest=sha256:a255b81f6abe9654030fdadffbcf2851ec0e9e2386a8e938c3f0b03ec21f41d0

Observation d28e90b0-fba3-4e07-a033-1a758f9d6c28 · outbound

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

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:16.087638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:16.087638Z digest=sha256:996ce8ba7677faaf0fce76b9e2dfdc0749071c43c1848b406bad27c5fee1028d

Observation f8f4b374-06fb-4c64-9209-d88f499887f4 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:16.192239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:16.192239Z digest=sha256:292037fb84677b90edf21597a7c19c54d2861eefbc04faf344ffcd0887f1550a

Observation 87e2d3cd-b5a2-4fb9-a928-9106961aa022 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 29

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:20.370283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:16.270706Z digest=sha256:2e15d3fb53355b4acfe9fa1a3e2250b7b3ffd09b66d6ab69fec456a3715b6ed7

Observation 54c745f4-3050-477b-8068-f03bf4ceca12 · outbound

This paper cites Backdoor Pre-trained Models Can Transfer to All.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Backdoor Pre-trained Models Can Transfer to All

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:16.387648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:16.387648Z digest=sha256:52ce5db5037cc241afaf7a517def397dd74f60bca5c3f9f73b2db15d96308004

Observation efce6e4a-a467-4b81-ba43-4873f940c9e4 · outbound

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

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:16.463357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:16.463357Z digest=sha256:e635a69bca11619c2f6c512758c959919411e5a907927ab36e54835a9384e904

Observation 94678c49-a97c-4893-a29e-7625c3932f6c · outbound

This paper cites Natural Backdoor Attack on Text Data.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Natural Backdoor Attack on Text Data

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:16.564496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:16.564496Z digest=sha256:5879908ffbb74dc192d48b96ddf8b2a57103233a9598c2e1d287ba5198ce4e38

Observation 8f37c53e-4e42-4872-8ad7-8768f1cbb690 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:16.682266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:16.682266Z digest=sha256:00f485b2c8552445e2a71d0cab93dfd2de6fd90bf033f21ec4b19f838901596c

Observation bb41e4cd-3760-4d38-bda8-7dbc1c2cf741 · outbound

This paper cites A Survey on Post-training of Large Language Models.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models A Survey on Post-training of Large Language Models

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:16.796706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:16.796706Z digest=sha256:546b63057529a3c01ea99c18203c0b6343068d3f23617a78be0b9f632476eb31

Observation b5a90ace-7812-4599-8dfd-9454d2acda22 · outbound

This paper cites OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:16.930344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:16.930344Z digest=sha256:0e86156d25f7e144079c68d519832ef79f26d82824ae774d48429743c76fbfc9

Observation 410606ef-b8cb-4e68-9396-c3383456b174 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 36

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:20.192074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:16.989693Z digest=sha256:90e589a1d840108e8b26c00b2f18605405d8ee9e387ad39d912d268e461baa95

Observation 06bd2291-f7f5-40c6-b46f-44af44752bf4 · outbound

This paper cites BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:17.082771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:17.082771Z digest=sha256:67796b7edd9da7cb86ea1318be5c7c28d05b73206b4e66b3fc58f1a658dd9ee6

Observation b3b8316c-34af-4bf1-8997-0cf804b4ed73 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:20.038255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:17.190393Z digest=sha256:e9ecb5f8bb755f8418616ad07241c8a957d34f45c2019d2b645ab8984e29caae

Observation 40d570c1-83d7-445c-a17a-f11a18c32c15 · outbound

This paper cites Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:17.286060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:17.286060Z digest=sha256:2c2a08788584d912130f6b264a559f08cb0c4c00835da1e2646f13b808546630

Observation d41db963-ae11-4a02-8fde-67a7f7aeec66 · outbound

This paper cites LoBAM: LoRA-Based Backdoor Attack on Model Merging.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models LoBAM: LoRA-Based Backdoor Attack on Model Merging

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:17.381752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:17.381752Z digest=sha256:0ab236e54079664e393d283a7e5a5dbbb5e34830abaa3e3fe4b82982b626a66c

Observation f58c5256-928a-4900-b765-b2a2ddaf0623 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 41

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:19.866248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:17.472251Z digest=sha256:437d5333f2ab46a36b2983fe32856770a000f71fbacfe87b9e5de9ca4d693fb3

Observation e021420d-0969-4ad8-92b9-c4ecd9881c5c · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:17.522018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:17.522018Z digest=sha256:4726e3ac80703a126ea7f4d94afb050c20bb91332d2b0d9a4926e596cc0e6a6a

Observation e8e11dcf-316f-4a1c-beeb-e7ed34875fd1 · outbound

This paper cites Backdoor Attacks to Pre-trained Unified Foundation Models.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Backdoor Attacks to Pre-trained Unified Foundation Models

Reference 43

Resolution
verified exact
local_arxiv, observed 2026-08-07T12:48:18.802405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:17.530699Z digest=sha256:560ae19d5f595cc2a0444fbaaf8cb2cbc73dcb027948b78b43a75391d4f0dc2d

Observation 5bc63c3d-ca04-4b37-a019-6d0c8586e2e4 · outbound

This paper cites BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

Reference 44

Resolution
verified exact
local_arxiv, observed 2026-08-07T12:48:18.598405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:17.634556Z digest=sha256:aa63b98c664d962bca3a91b8a847afedf82f690bd543293eb7c88ab470c71245

Observation b9c159d5-f586-40b6-bac1-4eaa004b529e · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 45

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:19.673919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:17.743822Z digest=sha256:4796af26d846b3c1a287b651348920c9fd0d1712f3bc90c10fb3d36517f39d6b

Observation aab23a1c-03bc-44ac-95ce-cef3c6e453a7 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:48:19.435511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T12:48:17.945186Z digest=sha256:b9d99577bcff0aa4ef9e2dd36b4fbfa85b928643a2a20e4f2e4d3e0ba27168b9

Observation 7ccd69a6-3948-4348-846b-b6b1ad5df634 · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:18.124491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:18.124491Z digest=sha256:2c33a30a94cfc85371ecdcd518fe867339a1acde0824c4188cb8900ad4d9e952

Observation 37612cec-ca52-40cc-ae6f-810bc7c7e8ac · outbound

This paper cites an unresolved cited work.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models Unresolved cited work

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:18.187357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:18.187357Z digest=sha256:6f2cc3ef91b2440781749004e24ea70d43abc70551ee6d5f1bf9c5c7f1a663e1

Observation 01995b97-26fe-470a-b7a2-684d3b70c197 · outbound

This paper cites online" 'onlinestring :=.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models online" 'onlinestring :=

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:18.290076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:18.290076Z digest=sha256:7d97015f2935c0127e7b24645d42ccc1433472a3c6215d787895694b50a5f0f2

Observation 899eec16-0269-495c-a375-8e4d0cdf62fd · outbound

This paper cites write newline.

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models write newline

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T12:48:18.371254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:48:18.371254Z digest=sha256:23d9c403c4d67d56b86007ce7942f5d62bf9784ffe9de4987a23c03d1814c714

Pith citing papers

Observation 936b7c5e-7ee8-4f31-beaf-2ec2303afdb1 · inbound

RogueMerge: Robust and Unified Attacks against LLM Model Merging cites this paper.

RogueMerge: Robust and Unified Attacks against LLM Model Merging Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

Reference 14

Resolution
verified exact
arxiv_id, observed 2026-07-02T03:26:29.008907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-06-28T10:05:10.309553Z digest=sha256:2a7d78924d06122f5387aadc4b47eb238f34d5564cdd11a7f66e68ed10f7a10e

Observation 62907152-6ace-4d7e-b61e-75d29ae90fc5 · inbound

From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging cites this paper.

From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-07-03T11:38:05.617172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-06-27T09:24:00.948230Z digest=sha256:bf39f6b807222484998fa7d7e6457164d5bbec461554138eb5e0da778b2e3924