Paper Citation Record · LEDGER

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment

As of 19 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2411.15673.

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

pith.paper-citation-record.v1
2411.15673 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T14:07:18.363722Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

20 of 20 outbound references displayed

verified exact1
verified fuzzy18
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 22cc8354-9241-43cb-b650-826a485d67b0 · outbound

This paper cites V ATT: trans- formers for multimodal self-supervised learning from raw video, audio and text.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment V ATT: trans- formers for multimodal self-supervised learning from raw video, audio and text

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.715323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 320f684f-ed65-414d-8b29-67f78e1d4313 · outbound

This paper cites Visual language maps for robot navigation.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Visual language maps for robot navigation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.627757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d4b8fff7-75ca-448b-8911-79d26e56e83c · outbound

This paper cites Align be- fore fuse: Vision and language representation learning with momentum distillation.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Align be- fore fuse: Vision and language representation learning with momentum distillation

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.611384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c2f1ac1c-45e3-4ff5-8eaf-a687ed8100d6 · outbound

This paper cites Backdoor defense with ma- chine unlearning.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Backdoor defense with ma- chine unlearning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.585104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1bf2b972-e3fa-492d-830f-284bda07ea97 · outbound

This paper cites Visual classification via de- scription from large language models.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Visual classification via de- scription from large language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.569126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 74debac1-6d2f-4efe-904e-7222293fee62 · outbound

This paper cites Deepsweep: An evalua- tion framework for mitigating dnn backdoor attacks using data augmentation.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Deepsweep: An evalua- tion framework for mitigating dnn backdoor attacks using data augmentation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.553331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2f76c2d9-5233-4d50-8aa7-45b26db67140 · outbound

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

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T14:07:18.324608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2b0e10-3a8f-4992-b6ae-ef0d3dca7ce6 · outbound

This paper cites How to train your vit? data, augmentation, and regularization in vision transformers.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment How to train your vit? data, augmentation, and regularization in vision transformers

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.525605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1ed620cc-5203-4ce9-b5d2-fe648741b603 · outbound

This paper cites Preserving se- mantic neighborhoods for robust cross-modal retrieval.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Preserving se- mantic neighborhoods for robust cross-modal retrieval

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.507999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 392d6bd5-9f0d-4a12-b3e5-7fd779d0948a · outbound

This paper cites Data poisoning attacks against federated learning systems.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Data poisoning attacks against federated learning systems

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.493933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 145791da-b677-432d-b099-8417b836afec · outbound

This paper cites Bppattack: Stealthy and efficient trojan attacks against deep neural networks via image quantization and contrastive adversar- ial learning.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Bppattack: Stealthy and efficient trojan attacks against deep neural networks via image quantization and contrastive adversar- ial learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.478825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f6b293d9-0425-4cfc-8ac6-60be33fdf246 · outbound

This paper cites Multimodal fake news detection via clip-guided learning.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Multimodal fake news detection via clip-guided learning

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.448083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1ee4be82-6a1b-4305-b664-16740eecdb1e · outbound

This paper cites Is data cluster- ing in adversarial settings secure? In Proceedings of the 2013 ACM Workshop on Artificial Intelligence and Secu- rity, page 87–98, New York, NY , USA, 2013a.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Is data cluster- ing in adversarial settings secure? In Proceedings of the 2013 ACM Workshop on Artificial Intelligence and Secu- rity, page 87–98, New York, NY , USA, 2013a

Reference 2012

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.678551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9c57a195-0c2c-4209-8775-b5d7b7efd9e4 · outbound

This paper cites CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning

Reference 2014

Resolution: verified exact; local_arxiv, observed 2026-08-12T14:07:18.412153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b120e6a1-ea11-4978-952a-cfd239354c0b · outbound

This paper cites Robust contrastive language-image pretraining against data poisoning and backdoor attacks.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Robust contrastive language-image pretraining against data poisoning and backdoor attacks

Reference 2015

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.464267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2c4d67cf-eb40-4f2e-8db8-18049c438504 · outbound

This paper cites Backdoor attack with imperceptible input and latent modification.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Backdoor attack with imperceptible input and latent modification

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.644195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c82d5844-03fb-480b-a3dd-4f5f2bbd7aa9 · outbound

This paper cites Backdoor attacks on self-supervised learning.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Backdoor attacks on self-supervised learning

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.538198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2a4e073c-c873-40a6-bdf8-331c20920284 · outbound

This paper cites Cleanclip: Mitigating data poisoning attacks in multimodal contrastive learning.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Cleanclip: Mitigating data poisoning attacks in multimodal contrastive learning

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.692860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a9017a94-1183-4791-a715-cbe08294a9c2 · outbound

This paper cites Anti-backdoor learning: Training clean models on poisoned data.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment Anti-backdoor learning: Training clean models on poisoned data

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.597792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 68a9d7d3-af63-4112-887a-1b7856fe504e · outbound

This paper cites org/blog/2023-03-30-vicuna, 1(2):3.

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment org/blog/2023-03-30-vicuna, 1(2):3

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:07:18.662806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

No inbound Pith citation observations are available.