Paper Citation Record · LEDGER

Detecting Backdoor Samples in Contrastive Language Image Pretraining

As of 9 August 2026, this Paper Citation Record lists 100 of 114 outbound references and 4 inbound Pith citation observations for arXiv:2502.01385.

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

pith.paper-citation-record.v1
2502.01385 v2

Coverage vector

measured 100 of 114 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T15:36:27.896710Z

measured 104 of 104 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:24:49.237522Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T19:15:00.862287Z

Reference resolution

100 of 114 outbound references displayed

verified exact1
verified fuzzy44
unresolved55
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6e62d8d0-f3d2-471b-bb63-0688dd74665b · outbound

This paper cites write newline.

Detecting Backdoor Samples in Contrastive Language Image Pretraining write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.423231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da69243e-97bb-4b30-a36d-94baa79fa591 · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining Flamingo: a visual language model for few-shot learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.430060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d032af2-0b2e-4744-94c0-8b33ffa082de · outbound

This paper cites Dimensionality-aware outlier detection: Theoretical and experimental analysis.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Dimensionality-aware outlier detection: Theoretical and experimental analysis

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.436078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66c045da-e77f-41cb-bafc-069d0c825181 · outbound

This paper cites Intrinsic dimension of data representations in deep neural networks.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Intrinsic dimension of data representations in deep neural networks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.441272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 985ade1e-0cf3-4153-a3e5-83384d01f2d5 · outbound

This paper cites OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models.

Detecting Backdoor Samples in Contrastive Language Image Pretraining OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.446261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0efd6974-3961-46f4-a22e-daf56fdba965 · outbound

This paper cites Blind backdoors in deep learning models.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Blind backdoors in deep learning models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.451675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c77f19a6-172c-434c-9287-e3dca119694a · outbound

This paper cites CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.456453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca0f1582-517e-49d6-8fe3-cabd6c4021d4 · outbound

This paper cites VICR eg: Variance-invariance-covariance regularization for self-supervised learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining VICR eg: Variance-invariance-covariance regularization for self-supervised learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.461804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 474b2a1c-1aac-4670-a2f1-0240cdd59a00 · outbound

This paper cites A new backdoor attack in cnns by training set corruption without label poisoning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining A new backdoor attack in cnns by training set corruption without label poisoning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.466731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d812ccc1-2bad-40a4-b562-14eec93cdfb1 · outbound

This paper cites Improving image generation with better captions.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Improving image generation with better captions

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.471524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f92e2b3-cd2b-41d2-adc3-4096ce7fb051 · outbound

This paper cites Poisoning Attacks against Support Vector Machines.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Poisoning Attacks against Support Vector Machines

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.476585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da66ad3b-2544-433f-b3f2-63bafc1b0bba · outbound

This paper cites Strong data augmentation sanitizes poisoning and backdoor attacks without an accuracy tradeoff.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Strong data augmentation sanitizes poisoning and backdoor attacks without an accuracy tradeoff

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.481833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d32f981-22d0-4953-8174-4382f1899f81 · outbound

This paper cites Food-101--mining discriminative components with random forests.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Food-101--mining discriminative components with random forests

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.486401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9c20830-a746-41d8-ad32-b375f10d3306 · outbound

This paper cites Lof: identifying density-based local outliers.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Lof: identifying density-based local outliers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.491089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fda0cca-0772-4b80-aa06-ba2c1414769f · outbound

This paper cites On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study.

Detecting Backdoor Samples in Contrastive Language Image Pretraining On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.495709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec137705-4c9b-4d48-bfd8-4c450c7bc7e2 · outbound

This paper cites Poisoning and backdooring contrastive learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Poisoning and backdooring contrastive learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.500654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c347cf5-b4a4-4ff7-9edf-6e7cae10ab46 · outbound

This paper cites Poisoning web-scale training datasets is practical.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Poisoning web-scale training datasets is practical

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.505627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e9e189c-5bc7-4917-8741-425a18af0e6e · outbound

This paper cites Emerging properties in self-supervised vision transformers.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Emerging properties in self-supervised vision transformers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.510418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9021f6db-3b76-4c5c-97a4-ae10e0b31ec3 · outbound

This paper cites Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.515324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be1fc8c6-4070-4b13-8bc8-3dd42e1738c1 · outbound

This paper cites Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.520230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17926085-3430-4304-8276-051431028dd7 · outbound

This paper cites Deepinspect: A black-box trojan detection and mitigation framework for deep neural networks.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Deepinspect: A black-box trojan detection and mitigation framework for deep neural networks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.525222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78836207-d456-4ef0-b5b1-3bdff2974f62 · outbound

This paper cites Effective backdoor defense by exploiting sensitivity of poisoned samples.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Effective backdoor defense by exploiting sensitivity of poisoned samples

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.529964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd3ea228-fa03-4cee-9aab-7e020a087e82 · outbound

This paper cites Exploring simple siamese representation learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Exploring simple siamese representation learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.534647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e37df2-36ff-4806-a336-6f0c151f0583 · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.539315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b90020b-9eb0-4819-ba61-c31485266648 · outbound

This paper cites Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-09T15:36:28.549651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b3f8629a-802f-40e5-80aa-f24d32dc2679 · outbound

This paper cites Learning a similarity metric discriminatively, with application to face verification.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Learning a similarity metric discriminatively, with application to face verification

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.549718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6f87f43-936d-46d2-9ba1-1dcfd6691039 · outbound

This paper cites An analysis of single-layer networks in unsupervised feature learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining An analysis of single-layer networks in unsupervised feature learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.554891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b25ac25-a34a-4601-9d68-c90e846fdb92 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Imagenet: A large-scale hierarchical image database

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.559965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7c0aa10-5208-46fc-a4cb-90d16403f579 · outbound

This paper cites Redcaps: Web-curated image-text data created by the people, for the people.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Redcaps: Web-curated image-text data created by the people, for the people

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.564801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e693dfbf-6fb8-4335-b0b0-3b1bd91940b2 · outbound

This paper cites Lira: Learnable, imperceptible and robust backdoor attacks.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Lira: Learnable, imperceptible and robust backdoor attacks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.569763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f70084ba-2fde-4def-afc4-cafd13bd2eae · outbound

This paper cites Collider: A robust training framework for backdoor data.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Collider: A robust training framework for backdoor data

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.574596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00ebc440-8aea-438e-832c-c2be279604af · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Detecting Backdoor Samples in Contrastive Language Image Pretraining An image is worth 16x16 words: Transformers for image recognition at scale

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.579415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2667f653-41a7-48e0-b11b-8c44fecf8e88 · outbound

This paper cites Detecting backdoors in pre-trained encoders.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Detecting backdoors in pre-trained encoders

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.584142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ed931bd-5367-4bec-b591-801306722f65 · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining Strip: A defence against trojan attacks on deep neural networks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.588907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35cea7c3-92ac-49f3-9c0b-0bb519ad7dcf · outbound

This paper cites Histogram-based outlier score (hbos): A fast unsupervised anomaly detection algorithm.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Histogram-based outlier score (hbos): A fast unsupervised anomaly detection algorithm

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.594028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8efd30b1-568b-434a-a937-c38036f15130 · outbound

This paper cites On the intrinsic dimensionality of image representations.

Detecting Backdoor Samples in Contrastive Language Image Pretraining On the intrinsic dimensionality of image representations

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.598891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1fc4423-3fb9-47a0-97b9-ed4d3cc0f61e · outbound

This paper cites Bootstrap your own latent-a new approach to self-supervised learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Bootstrap your own latent-a new approach to self-supervised learning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.603558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb63086e-b6d2-4c10-9663-e71c5f0864aa · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.608322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac9ceb08-06a7-4aab-ad5a-efee1ab10324 · outbound

This paper cites Dimensionality reduction by learning an invariant mapping.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Dimensionality reduction by learning an invariant mapping

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.613278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26013707-6026-4968-89dc-b45bd6e34656 · outbound

This paper cites Defense against backdoor attacks via robust covariance estimation.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Defense against backdoor attacks via robust covariance estimation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.617973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d030873a-24cd-4ed5-9bae-e0ada5355591 · outbound

This paper cites Deep residual learning for image recognition.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Deep residual learning for image recognition

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.622992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c8a811-b849-4633-a903-caa0ce215f78 · outbound

This paper cites IBD - PSC : Input-level backdoor detection via parameter-oriented scaling consistency.

Detecting Backdoor Samples in Contrastive Language Image Pretraining IBD - PSC : Input-level backdoor detection via parameter-oriented scaling consistency

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.556234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1ea47e0f-1c9b-4a9d-8a22-616219c0abab · outbound

This paper cites Local intrinsic dimensionality I : an extreme-value-theoretic foundation for similarity applications.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Local intrinsic dimensionality I : an extreme-value-theoretic foundation for similarity applications

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.542060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation aa63ad14-edc3-4493-9579-120e7d883266 · outbound

This paper cites On the correlation between local intrinsic dimensionality and outlierness.

Detecting Backdoor Samples in Contrastive Language Image Pretraining On the correlation between local intrinsic dimensionality and outlierness

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.526270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d57b3193-c431-4d6c-a8e6-8d2c8d495d0a · outbound

This paper cites Trigger hunting with a topological prior for trojan detection.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Trigger hunting with a topological prior for trojan detection

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.509258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5a5c5148-2d9a-416b-a932-f851f8055980 · outbound

This paper cites Distilling cognitive backdoor patterns within an image.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Distilling cognitive backdoor patterns within an image

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.493532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cc7f8688-8a83-49fc-91b6-2b023d702711 · outbound

This paper cites an unresolved cited work.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-09T15:36:29.476878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 514134ed-8952-4de1-af05-0053b4c8f4ab · outbound

This paper cites Backdoor defense via decoupling the training process.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Backdoor defense via decoupling the training process

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.461789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f2fad332-eee8-4cb9-993d-fc0ec41456c8 · outbound

This paper cites Openclip, 2021.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Openclip, 2021

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.447552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cc562bb9-0f17-481a-b4fe-7f4a5db4ef76 · outbound

This paper cites Scaling up visual and vision-language representation learning with noisy text supervision.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Scaling up visual and vision-language representation learning with noisy text supervision

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.665650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15186d00-b367-40de-844e-ee53f214f827 · outbound

This paper cites Badencoder: Backdoor attacks to pre-trained encoders in self-supervised learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Badencoder: Backdoor attacks to pre-trained encoders in self-supervised learning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.424455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b0289448-ff3a-411e-9a6c-28eff072c92c · outbound

This paper cites Bayesian estimation approaches for local intrinsic dimensionality.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Bayesian estimation approaches for local intrinsic dimensionality

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.410530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3c60dfbb-a831-4f5a-b9cf-7c6b05047126 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Adam: A Method for Stochastic Optimization

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.680343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11e21227-0c38-403c-ba53-179037258906 · outbound

This paper cites Universal litmus patterns: Revealing backdoor attacks in cnns.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Universal litmus patterns: Revealing backdoor attacks in cnns

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.396063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 43ee95b1-9a8a-41f6-a254-7b650ac68a50 · outbound

This paper cites Collecting a large-scale dataset of fine-grained cars.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Collecting a large-scale dataset of fine-grained cars

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.689967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87ec1d2-ad42-4669-b207-1d8673c7468c · outbound

This paper cites Angle-based outlier detection in high-dimensional data.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Angle-based outlier detection in high-dimensional data

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.372021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f5693886-fc3e-4fb3-b101-b65fbda97da1 · outbound

This paper cites Learning multiple layers of features from tiny images.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Learning multiple layers of features from tiny images

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.699179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b349c7b5-7f4f-4fde-a900-882f7c08754c · outbound

This paper cites Adversarial Backdoor Defense in CLIP.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Adversarial Backdoor Defense in CLIP

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.703899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da0b0b29-26a5-4b77-8a45-6c3ddb763404 · outbound

This paper cites Outlier detection with kernel density functions.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Outlier detection with kernel density functions

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.348185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 72396ffb-ff4f-4a31-b550-abe6732d2d7c · outbound

This paper cites Feature bagging for outlier detection.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Feature bagging for outlier detection

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.334406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0bd7d9b4-82b5-4a89-bff6-d16da1f5ae48 · outbound

This paper cites Maximum likelihood estimation of intrinsic dimension.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Maximum likelihood estimation of intrinsic dimension

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.320366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b226de63-fa6b-4a22-9779-ce520df16a24 · outbound

This paper cites An embarrassingly simple backdoor attack on self-supervised learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining An embarrassingly simple backdoor attack on self-supervised learning

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.306678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 41baecc6-c532-4b2a-944e-ac4ea0635a48 · outbound

This paper cites On the difficulty of defending contrastive learning against backdoor attacks.

Detecting Backdoor Samples in Contrastive Language Image Pretraining On the difficulty of defending contrastive learning against backdoor attacks

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.291582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 678076d2-b537-47df-8d20-2a09922ef440 · outbound

This paper cites Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.275635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 053e3ccf-ded3-40f6-9c65-6d1aae42c699 · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining Anti-backdoor learning: Training clean models on poisoned data

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.260999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 94a0ba09-7d08-4c67-919e-dd5aa9069683 · outbound

This paper cites Multi-trigger backdoor attacks: More triggers, more threats.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Multi-trigger backdoor attacks: More triggers, more threats

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.742349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 604327b0-2b58-40cf-808b-e33b5d221ebd · outbound

This paper cites Rethinking the Trigger of Backdoor Attack.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Rethinking the Trigger of Backdoor Attack

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.749419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1645f2b-037a-444e-aa43-5d6f5fc6dda5 · outbound

This paper cites Ecod: Unsupervised outlier detection using empirical cumulative distribution functions.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Ecod: Unsupervised outlier detection using empirical cumulative distribution functions

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.246793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4fada96f-461a-4302-a2bb-2f98cb837221 · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining Composite backdoor attack for deep neural network by mixing existing benign features

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.232307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 40fddac8-d2a9-460b-92d4-173c27bb9cca · outbound

This paper cites Isolation forest.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Isolation forest

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.216160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b29b16c5-2068-4ad9-b228-bc431942829a · outbound

This paper cites Visual instruction tuning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Visual instruction tuning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.767917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdb9b8f-ef39-4066-a641-68802fc3aa94 · outbound

This paper cites \ PoisonedEncoder \ : Poisoning the unlabeled pre-training data in contrastive learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining \ PoisonedEncoder \ : Poisoning the unlabeled pre-training data in contrastive learning

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.192783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1cb7c0bf-db47-4359-be66-eac1ab68f09a · outbound

This paper cites Trojaning attack on neural networks.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Trojaning attack on neural networks

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.177924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 953c1ab6-9253-4eef-a255-ee10cd6ae07c · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining Abs: Scanning neural networks for back-doors by artificial brain stimulation

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.163279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5400d521-69b4-42f5-a9be-ca2bfa0027d2 · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining Reflection backdoor: A natural backdoor attack on deep neural networks

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.148272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 40a22546-8e58-4823-8530-e62f3045918d · outbound

This paper cites Decoupled weight decay regularization.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Decoupled weight decay regularization

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.790894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e949240-2430-45cd-a2dc-39b10c06e0cd · outbound

This paper cites Erfani, Sudanthi Wijewickrema, Grant Schoenebeck, Michael E.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Erfani, Sudanthi Wijewickrema, Grant Schoenebeck, Michael E

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.124187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c178b975-fb4a-4766-9fe0-b62b67082261 · outbound

This paper cites Dimensionality-driven learning with noisy labels.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Dimensionality-driven learning with noisy labels

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.108658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ffaf42e5-deb7-4360-9012-dbce364e3b6f · outbound

This paper cites Excess capacity and backdoor poisoning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Excess capacity and backdoor poisoning

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.093341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f70f744e-e8cd-4566-a117-36c2ba9cd73a · outbound

This paper cites Wanet - imperceptible warping-based backdoor attack.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Wanet - imperceptible warping-based backdoor attack

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.078970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 62d7a3d6-8ede-4d31-917e-116e2a173a4c · outbound

This paper cites Bdetclip: Multimodal prompting contrastive test-time backdoor detection.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Bdetclip: Multimodal prompting contrastive test-time backdoor detection

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.814044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7661b480-ac89-4c62-b70e-2080c9cafe37 · outbound

This paper cites Loci: Fast outlier detection using the local correlation integral.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Loci: Fast outlier detection using the local correlation integral

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.064758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 79528a3f-c91a-430e-bbea-1194d8fe540a · outbound

This paper cites Incremental local outlier detection for data streams.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Incremental local outlier detection for data streams

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.050583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c25c9e16-5fd2-4f86-af0d-30cd62a76972 · outbound

This paper cites The intrinsic dimension of images and its impact on learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining The intrinsic dimension of images and its impact on learning

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.035886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d593c270-291d-455c-b2a6-772f78adf624 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Learning transferable visual models from natural language supervision

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.831629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d16f488d-3e9d-4710-899e-e024e121da40 · outbound

This paper cites Efficient algorithms for mining outliers from large data sets.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Efficient algorithms for mining outliers from large data sets

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:29.012869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ab6233ef-8de7-49d3-a987-3a93156c7220 · outbound

This paper cites Fast memory efficient local outlier detection in data streams.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Fast memory efficient local outlier detection in data streams

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.998787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e7d1d1b6-8a3d-4fa9-83c0-f3794f1d8f62 · outbound

This paper cites A new algorithm for detecting outliers in linear regression.

Detecting Backdoor Samples in Contrastive Language Image Pretraining A new algorithm for detecting outliers in linear regression

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.984568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation db95a472-538e-4eb5-a0b2-f6bd4ff6b211 · outbound

This paper cites Local outlier detection reconsidered: a generalized view on locality with applications to spatial, video, and network outlier detection.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Local outlier detection reconsidered: a generalized view on locality with applications to spatial, video, and network outlier detection

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.970491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dc4f8714-8ca8-4821-a26d-679630c7ca7c · outbound

This paper cites Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.853252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfaa2bea-16e7-4e2f-97c7-8e2b1427798a · outbound

This paper cites Manipulating sgd with data ordering attacks.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Manipulating sgd with data ordering attacks

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.946535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ae5e993a-8728-4143-a2fe-9bd54e48b22a · outbound

This paper cites an unresolved cited work.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Unresolved cited work

Reference 92

Resolution: unresolved; raw_fallback, observed 2026-08-09T15:36:28.931212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c5554c61-930a-4ee2-823c-23be884731a7 · outbound

This paper cites Backdoor contrastive learning via bi-level trigger optimization.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Backdoor contrastive learning via bi-level trigger optimization

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.915808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a07c85b5-f511-412c-b37e-e4b2042c28cc · outbound

This paper cites Demon in the variant: Statistical analysis of \ DNNs \ for robust backdoor contamination detection.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Demon in the variant: Statistical analysis of \ DNNs \ for robust backdoor contamination detection

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.901890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b97c737c-398b-4531-af8c-0a0e1b9ccf33 · outbound

This paper cites Enhancing effectiveness of outlier detections for low density patterns.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Enhancing effectiveness of outlier detections for low density patterns

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.887919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a7247348-81b2-4103-af2d-d409e9015f34 · outbound

This paper cites Distribution preserving backdoor attack in self-supervised learning.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Distribution preserving backdoor attack in self-supervised learning

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.874041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation abab87c6-d6fb-4700-8137-b2eb9717aef1 · outbound

This paper cites Spectral signatures in backdoor attacks.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Spectral signatures in backdoor attacks

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.860094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3290789c-8d5a-4602-88c0-628d81894d43 · outbound

This paper cites Clean-label backdoor attacks.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Clean-label backdoor attacks

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-09T15:36:27.887710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cc80c40-c1df-4e1d-922e-27a5e3ef903f · outbound

This paper cites Attention is all you need.

Detecting Backdoor Samples in Contrastive Language Image Pretraining Attention is all you need

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.836594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 00c63bbd-c0b8-4614-862e-9fd66aec96d4 · outbound

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

Detecting Backdoor Samples in Contrastive Language Image Pretraining Neural cleanse: Identifying and mitigating backdoor attacks in neural networks

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T15:36:28.822553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation 1f8f4eb6-b1a1-489d-8f94-7d3860a6e7ed · inbound

From Detection to Correction: Backdoor-Resilient Face Recognition via Vision-Language Trigger Detection and Noise-Based Neutralization cites this paper.

From Detection to Correction: Backdoor-Resilient Face Recognition via Vision-Language Trigger Detection and Noise-Based Neutralization Detecting Backdoor Samples in Contrastive Language Image Pretraining

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-05T23:24:49.237522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c065ca8-61da-4f9d-8463-d99127c8496e · inbound

CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion cites this paper.

CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion Detecting Backdoor Samples in Contrastive Language Image Pretraining

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:00:58.873663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bb75ab51-17cf-4b5e-ae1c-57c3e6a411f7 · inbound

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations cites this paper.

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations Detecting Backdoor Samples in Contrastive Language Image Pretraining

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-20T18:23:37.726629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 48d275ea-fab8-431a-99b0-34012037be22 · inbound

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations cites this paper.

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations Detecting Backdoor Samples in Contrastive Language Image Pretraining

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:15:00.864184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.