Paper Citation Record · LEDGER

Robust Anti-Backdoor Instruction Tuning in LVLMs

As of 17 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 3 inbound Pith citation observations for arXiv:2506.05401.

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

pith.paper-citation-record.v1
2506.05401 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:07:37.498468Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T05:29:52.758898Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T05:31:07.660447Z

Reference resolution

41 of 41 outbound references displayed

verified exact2
verified fuzzy17
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b868d0c8-acc0-4e78-9db4-aaa044a65def · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

Robust Anti-Backdoor Instruction Tuning in LVLMs Flamingo: a visual language model for few-shot learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.357327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e3f0c30-c293-446c-b31c-1486003f2cbf · outbound

This paper cites MIMIC-IT: Multi-Modal In-Context Instruction Tuning.

Robust Anti-Backdoor Instruction Tuning in LVLMs MIMIC-IT: Multi-Modal In-Context Instruction Tuning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.361566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee69dab6-8745-4afb-82ae-d273463a5777 · outbound

This paper cites Llava-plus: Learning to use tools for creating multimodal agents.

Robust Anti-Backdoor Instruction Tuning in LVLMs Llava-plus: Learning to use tools for creating multimodal agents

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.365712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b45a841b-6072-4d24-aab5-b61a0c8e4d18 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Robust Anti-Backdoor Instruction Tuning in LVLMs Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.369572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23ae39c0-a358-4a92-a27a-81743846319c · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Robust Anti-Backdoor Instruction Tuning in LVLMs MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.373024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e7090f-091c-4b21-ae5f-22ba23a9d536 · outbound

This paper cites Vqa: Visual question answering.

Robust Anti-Backdoor Instruction Tuning in LVLMs Vqa: Visual question answering

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.973390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4304e154-09c0-46ff-b006-22d2000be5c6 · outbound

This paper cites A comprehensive survey of deep learning for image captioning.

Robust Anti-Backdoor Instruction Tuning in LVLMs A comprehensive survey of deep learning for image captioning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.962698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 681306c8-4bfb-40d1-b505-896a2a39e54d · outbound

This paper cites Visual navigation for mobile robots: A survey.

Robust Anti-Backdoor Instruction Tuning in LVLMs Visual navigation for mobile robots: A survey

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.952455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e55191d2-765f-431f-9d21-c3b2554f12c0 · outbound

This paper cites Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review.

Robust Anti-Backdoor Instruction Tuning in LVLMs Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.386575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05021b72-fa5e-4f09-96e4-f59588c51430 · outbound

This paper cites Badclip: Dual- embedding guided backdoor attack on multimodal contrastive learning.

Robust Anti-Backdoor Instruction Tuning in LVLMs Badclip: Dual- embedding guided backdoor attack on multimodal contrastive learning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.942376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 713d62c3-4024-4982-9f7d-ef9dc8244ee7 · outbound

This paper cites Pre-trained Trojan Attacks for Visual Recognition.

Robust Anti-Backdoor Instruction Tuning in LVLMs Pre-trained Trojan Attacks for Visual Recognition

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.393240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9d73cf5-804b-47de-9ac9-d87fd398a0fe · outbound

This paper cites Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection.

Robust Anti-Backdoor Instruction Tuning in LVLMs Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.397004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 635d9011-ed56-4fa0-9c83-21513e66c517 · outbound

This paper cites Towards Robust Physical-world Backdoor Attacks on Lane Detection.

Robust Anti-Backdoor Instruction Tuning in LVLMs Towards Robust Physical-world Backdoor Attacks on Lane Detection

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.404099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7ca5614-e7dd-4bd1-9701-f9fbf69106a6 · outbound

This paper cites Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack.

Robust Anti-Backdoor Instruction Tuning in LVLMs Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.407964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18b3f355-f8f6-46e0-97db-9470e5b3e604 · outbound

This paper cites Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift.

Robust Anti-Backdoor Instruction Tuning in LVLMs Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.411521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16fec0e2-bd22-4f0b-b475-0032b4a95ff0 · outbound

This paper cites Compromising Embodied Agents with Contextual Backdoor Attacks.

Robust Anti-Backdoor Instruction Tuning in LVLMs Compromising Embodied Agents with Contextual Backdoor Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.414931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb13aa0d-ec64-462d-b814-3abe343266cb · outbound

This paper cites BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks.

Robust Anti-Backdoor Instruction Tuning in LVLMs BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:07:37.674530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 067e887d-1b90-4fc6-9a5d-90c63825849f · outbound

This paper cites Universal Backdoor Attacks Detection via Adaptive Adversarial Probe.

Robust Anti-Backdoor Instruction Tuning in LVLMs Universal Backdoor Attacks Detection via Adaptive Adversarial Probe

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.421870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3ef40e5-d86e-4de6-9b10-da8f03abdf49 · outbound

This paper cites Neural cleanse: Identifying and mitigating backdoor attacks in neural networks.

Robust Anti-Backdoor Instruction Tuning in LVLMs Neural cleanse: Identifying and mitigating backdoor attacks in neural networks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.931945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 03b5b41a-55c7-4de8-aea3-21819cccd7d5 · outbound

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

Robust Anti-Backdoor Instruction Tuning in LVLMs Fine-pruning: Defending against backdooring attacks on deep neural networks

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.920651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0b6e993a-f242-456d-be55-a22b672db3a5 · outbound

This paper cites Strip: A defence against trojan attacks on deep neural networks.

Robust Anti-Backdoor Instruction Tuning in LVLMs Strip: A defence against trojan attacks on deep neural networks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.432133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81876ca6-3fb0-4a50-9b38-1696379ded55 · outbound

This paper cites Cfbd: Coarse-to-fine detection of backdoor attacks in multimodal contrastive learning.

Robust Anti-Backdoor Instruction Tuning in LVLMs Cfbd: Coarse-to-fine detection of backdoor attacks in multimodal contrastive learning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.903901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c999a4cf-7cc7-4cbd-9cd1-c37cfface173 · outbound

This paper cites BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger.

Robust Anti-Backdoor Instruction Tuning in LVLMs BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:07:37.649786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2dbaafcd-0772-44ee-9063-6cb6aa03aa0b · outbound

This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.

Robust Anti-Backdoor Instruction Tuning in LVLMs InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.442346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac7878de-ab01-4ce2-b298-dc3e60e33923 · outbound

This paper cites Badnets: Evaluating backdooring attacks on deep neural networks.

Robust Anti-Backdoor Instruction Tuning in LVLMs Badnets: Evaluating backdooring attacks on deep neural networks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.892582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9fdac35d-809b-486d-b4c6-be5f37ba56b2 · outbound

This paper cites Invisible backdoor attack with sample-specific triggers.

Robust Anti-Backdoor Instruction Tuning in LVLMs Invisible backdoor attack with sample-specific triggers

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.881155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 34519cc7-c44f-47f4-b087-b9832d010b3e · outbound

This paper cites Reflection backdoor: A natural backdoor attack on deep neural networks.

Robust Anti-Backdoor Instruction Tuning in LVLMs Reflection backdoor: A natural backdoor attack on deep neural networks

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.869990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 188e2eea-dc96-444e-9cdf-8a53e1f92ddd · outbound

This paper cites Backdoor Attack through Frequency Domain.

Robust Anti-Backdoor Instruction Tuning in LVLMs Backdoor Attack through Frequency Domain

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.455570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9453b33-e959-4fec-a970-4fc9962a2a5e · outbound

This paper cites Badclip: Trigger-aware prompt learning for backdoor attacks on clip.

Robust Anti-Backdoor Instruction Tuning in LVLMs Badclip: Trigger-aware prompt learning for backdoor attacks on clip

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.858949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c4ee062e-5b6e-47f2-aeca-55edf2c1d653 · outbound

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

Robust Anti-Backdoor Instruction Tuning in LVLMs VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.462457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f2a7be7-8073-4578-881b-cf7c0ceffe10 · outbound

This paper cites Defending multimodal backdoored models by repulsive visual prompt tuning.

Robust Anti-Backdoor Instruction Tuning in LVLMs Defending multimodal backdoored models by repulsive visual prompt tuning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.465496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce754955-4d2a-41fc-ae46-6198ee1d6c37 · outbound

This paper cites Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning.

Robust Anti-Backdoor Instruction Tuning in LVLMs Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.468693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 753507c0-c02a-48c0-a87c-73ec5a8856db · outbound

This paper cites Spectral signatures in backdoor attacks.

Robust Anti-Backdoor Instruction Tuning in LVLMs Spectral signatures in backdoor attacks

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.848310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 966ac803-6b86-43a5-ac73-1d3d92e32a9e · outbound

This paper cites Dual-key multimodal backdoors for visual question answering.

Robust Anti-Backdoor Instruction Tuning in LVLMs Dual-key multimodal backdoors for visual question answering

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.838206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0cc2925d-277d-4185-8c7f-3f9fd9b4523c · outbound

This paper cites Microsoft coco: Common objects in context.

Robust Anti-Backdoor Instruction Tuning in LVLMs Microsoft coco: Common objects in context

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.478573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e842ba6-34e9-4432-9627-2bd1bfdf124c · outbound

This paper cites Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models.

Robust Anti-Backdoor Instruction Tuning in LVLMs Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.822513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3326d994-afe6-48f8-815f-39099d32b923 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation.

Robust Anti-Backdoor Instruction Tuning in LVLMs Bleu: a method for automatic evaluation of machine translation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.485067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 987ed5fc-9422-49bc-972c-e74b452debf8 · outbound

This paper cites Meteor: An automatic metric for mt evaluation with improved correlation with human judgments.

Robust Anti-Backdoor Instruction Tuning in LVLMs Meteor: An automatic metric for mt evaluation with improved correlation with human judgments

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.806633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 81ef931a-4170-4744-a5ec-87778dac1241 · outbound

This paper cites Rouge: A package for automatic evaluation of summaries.

Robust Anti-Backdoor Instruction Tuning in LVLMs Rouge: A package for automatic evaluation of summaries

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:37.491797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4ff05ae-21b0-455e-9826-b62d20728772 · outbound

This paper cites Cider: Consensus-based image description evaluation.

Robust Anti-Backdoor Instruction Tuning in LVLMs Cider: Consensus-based image description evaluation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.789269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cc02b70a-9ec0-417b-ba73-e2b75d1cd714 · outbound

This paper cites Spice: Semantic propositional image caption evaluation.

Robust Anti-Backdoor Instruction Tuning in LVLMs Spice: Semantic propositional image caption evaluation

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:37.778853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation e2e9d226-d3c3-4433-a8a1-fde450d50091 · inbound

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models cites this paper.

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models Robust Anti-Backdoor Instruction Tuning in LVLMs

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:05:49.185883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7c69b674-2df9-42c1-9dcf-c84db03c0512 · inbound

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy cites this paper.

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy Robust Anti-Backdoor Instruction Tuning in LVLMs

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:48:57.434708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8896ba9e-107e-48bb-bc85-f3776bfec02b · inbound

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting cites this paper.

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting Robust Anti-Backdoor Instruction Tuning in LVLMs

Reference 123

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:31:07.663218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.