Paper Citation Record · LEDGER

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs

As of 11 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2501.15478.

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

pith.paper-citation-record.v1
2501.15478 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:19:18.429691Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T06:39:15.694127Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T14:33:30.980901Z

Reference resolution

44 of 44 outbound references displayed

verified exact1
verified fuzzy33
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f59722c8-6baf-447d-b606-6a12fe33d409 · outbound

This paper cites Turning your weakness into a strength: Watermarking deep neural net- works by backdooring.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Turning your weakness into a strength: Watermarking deep neural net- works by backdooring

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.220548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2aa18c4e-d931-4efd-98dd-1869dc6ddfee · outbound

This paper cites Scalable watermarking for identifying large language model outputs.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Scalable watermarking for identifying large language model outputs

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.160328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7a0b75a9-7b42-45d0-a355-4614593f6dd3 · outbound

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

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs LoRA: Low-Rank Adaptation of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.257252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 603a7907-6823-4e28-80aa-0892cdff74db · outbound

This paper cites https://huggingface.co/models?search=lora,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs https://huggingface.co/models?search=lora,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.100579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d94f3786-d40f-4155-9870-69fa22ca91d2 · outbound

This paper cites Subnetwork-lossless robust watermarking for hostile theft attacks in deep transfer learning models.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Subnetwork-lossless robust watermarking for hostile theft attacks in deep transfer learning models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.069200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8b9160fc-7b21-4681-995d-d292a6426545 · outbound

This paper cites Credid: Credible multi-bit watermark for large language models identification,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Credid: Credible multi-bit watermark for large language models identification,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.053220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b00759ea-0db7-4d6e-8dbc-e212e3c0a08e · outbound

This paper cites A watermark for large language models.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs A watermark for large language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.037923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e0bb0d80-d685-419e-b322-6f19a6db93a5 · outbound

This paper cites Fedipr: Ownership verification for federated deep neural network models.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Fedipr: Ownership verification for federated deep neural network models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.022237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6545b0d9-1163-46a5-bb20-aa5949390721 · outbound

This paper cites Aesthetic post-training diffusion models from generic preferences with step-by-step preference optimiza- tion,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Aesthetic post-training diffusion models from generic preferences with step-by-step preference optimiza- tion,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.006226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 318f2164-3361-45e6-9015-fa80adb09f3f · outbound

This paper cites Abs: Scanning neural networks for back-doors by artificial brain stimulation.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Abs: Scanning neural networks for back-doors by artificial brain stimulation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.991143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6a8dea77-f83a-43e7-9a13-08f5b95c5a37 · outbound

This paper cites SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.310448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48a13c93-aa94-48fd-ab0c-0db7daad39a7 · outbound

This paper cites MEA-Defender: A Robust Watermark against Model Extraction Attack.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs MEA-Defender: A Robust Watermark against Model Extraction Attack

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-10T14:19:18.640798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5ec9a17e-1a84-423e-9a48-b0e7746ea8ee · outbound

This paper cites Clora: A contrastive approach to compose multiple lora models,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Clora: A contrastive approach to compose multiple lora models,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.975471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fb68f099-c64a-493d-868a-df7d0b43f28e · outbound

This paper cites A Watermark-Conditioned Diffusion Model for IP Protection.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs A Watermark-Conditioned Diffusion Model for IP Protection

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.325721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5d40d9-67b4-4416-b97c-da613de19877 · outbound

This paper cites Exploitation of generative ai by terrorist groups,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Exploitation of generative ai by terrorist groups,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.960497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5015a437-1f73-4e3d-8836-394b07777312 · outbound

This paper cites En- semble watermarks for large language models,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs En- semble watermarks for large language models,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.945479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e46f3fe8-e202-4947-8865-e9cb96710fa5 · outbound

This paper cites On aliased resizing and surprising subtleties in gan evaluation.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs On aliased resizing and surprising subtleties in gan evaluation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.929190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d2e08489-790b-468a-a56a-92ef3bd6a843 · outbound

This paper cites Onion: A simple and effective defense against textual backdoor attacks,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Onion: A simple and effective defense against textual backdoor attacks,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.913687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 98cf97ee-d977-4efe-b8f7-ab9d62984b1c · outbound

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

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Improving language understanding by generative pre-training

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.897117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f4e87c26-e817-48bf-b373-121365c91f8b · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.353694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96c64df0-fed6-43f0-b4a4-ad7672216cc8 · outbound

This paper cites Waterdiff: Perceptual image wa- termarks via diffusion model.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Waterdiff: Perceptual image wa- termarks via diffusion model

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.881573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f3c5a1a9-bf7d-4b6b-84c2-2ed758f2d0ea · outbound

This paper cites Waffle: Watermarking in fed- erated learning.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Waffle: Watermarking in fed- erated learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.865632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d4b4674d-2c6f-4610-8119-f29a0170c003 · outbound

This paper cites Embedding watermarks into deep neural networks.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Embedding watermarks into deep neural networks

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.850690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0bc40717-61bd-421f-8487-6c119d291c78 · outbound

This paper cites an unresolved cited work.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:19:18.818949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 075b5e33-af9c-4ed4-a8be-90e3060593f5 · outbound

This paper cites Multilora: Democratizing lora for better multi-task learning,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Multilora: Democratizing lora for better multi-task learning,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.804132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ea2d29cb-8b0f-43d8-9764-58e6be593e33 · outbound

This paper cites Ad- versarial neuron pruning purifies backdoored deep models.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Ad- versarial neuron pruning purifies backdoored deep models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.788048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1921519d-9e07-4284-a062-a708c3a655d0 · outbound

This paper cites Robust multi-bit text watermark with llm-based paraphrasers,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Robust multi-bit text watermark with llm-based paraphrasers,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.769797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 05c429e6-5609-4b5e-a177-34e7bda2761a · outbound

This paper cites Rap: Robustness-aware perturba- tions for defending against backdoor attacks on nlp models,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Rap: Robustness-aware perturba- tions for defending against backdoor attacks on nlp models,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.752676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0466337d-8db6-43b3-8cd0-cd0768beba1a · outbound

This paper cites IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.400526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3727e156-0c8a-4942-b1b1-f2db7e4cc733 · outbound

This paper cites EcoAct: Economic Agent Determines When to Register What Action.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs EcoAct: Economic Agent Determines When to Register What Action

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.405463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb395933-f68d-4ada-870a-cf919bd4c0e0 · outbound

This paper cites A Recipe for Watermarking Diffusion Models.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs A Recipe for Watermarking Diffusion Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.410367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fafa4d30-7a48-4db3-918f-818242f260e0 · outbound

This paper cites Understanding and improving adver- sarial attacks on latent diffusion model.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Understanding and improving adver- sarial attacks on latent diffusion model

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.415059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96077170-d12e-48b2-92b0-c8461849f008 · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Llamafactory: Unified efficient fine-tuning of 100+ language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.736860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8870d237-d79f-4984-b4cf-c3b79266437d · outbound

This paper cites [Zhong et al., 2024] Ming Zhong, Yelong Shen, Shuohang Wang, Yadong Lu, Yizhu Jiao, Siru Ouyang, Donghan Yu, Jiawei Han, and Weizhu Chen.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs [Zhong et al., 2024] Ming Zhong, Yelong Shen, Shuohang Wang, Yadong Lu, Yizhu Jiao, Siru Ouyang, Donghan Yu, Jiawei Han, and Weizhu Chen

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.721059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation aaad98ec-dbad-4e2c-9b26-b6727dcd3764 · outbound

This paper cites Watermark-embedded adversarial ex- amples for copyright protection against diffusion models.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Watermark-embedded adversarial ex- amples for copyright protection against diffusion models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.705665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 01d44ca6-05fc-43c5-9cc1-4b46bb73297f · outbound

This paper cites Lapointe, 2024] Simon Dub´e Valerie A.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Lapointe, 2024] Simon Dub´e Valerie A

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:18.835013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 059c5bff-5160-4df3-bd73-8e9576281601 · outbound

This paper cites Task arithmetic with lora for continual learning,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Task arithmetic with lora for continual learning,

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.205211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation aecc6d95-655b-4c81-8c73-0c11cfb9e117 · outbound

This paper cites Watermarking Diffusion Model.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Watermarking Diffusion Model

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T14:19:18.304784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dda308ea-ad95-42dc-8416-438de7b25e2f · outbound

This paper cites Aqualora: Toward white-box protection for customized stable diffusion models via wa- termark lora,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Aqualora: Toward white-box protection for customized stable diffusion models via wa- termark lora,

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.130298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 68eab9b0-e219-4636-8126-60e28e71248c · outbound

This paper cites Lorahub: Efficient cross-task generalization via dynamic lora composition,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Lorahub: Efficient cross-task generalization via dynamic lora composition,

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.115634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 39d7e29b-4cab-4136-8c7b-627a9d522bfd · outbound

This paper cites Unsloth,.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Unsloth,

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.174395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4a6cbaf7-2ead-4da5-9726-8774b220ed4b · outbound

This paper cites Sslguard: A watermarking scheme for self- supervised learning pre-trained encoders.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Sslguard: A watermarking scheme for self- supervised learning pre-trained encoders

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.189657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation eabae216-17ae-4f3e-b99d-6a6d0928abc6 · outbound

This paper cites Ranasinghe.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Ranasinghe

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.145303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 532b1b2d-d999-4366-9028-15495f58a524 · outbound

This paper cites Entangled watermarks as a defense against model extraction.

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs Entangled watermarks as a defense against model extraction

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:19:19.085020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

Observation f93eb6ee-34f8-4767-933c-52e05eeabea7 · inbound

LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models cites this paper.

LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:33:30.982415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.