Paper Citation Record · LEDGER

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images

As of 13 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2412.08755.

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

pith.paper-citation-record.v1
2412.08755 v4

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T17:40:15.084723Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T17:40:14.957458Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-11T17:40:15.255674Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy23
unresolved9
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 54731f6c-02f1-4b13-9c4e-3348e9864dd4 · outbound

This paper cites Mvitv2: Improved multiscale vision transformers for classification and de- tection,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Mvitv2: Improved multiscale vision transformers for classification and de- tection,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.635548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c23245d3-d15b-48ab-8ddf-2e1d352f9e6b · outbound

This paper cites Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images

Reference 2

Resolution: malformed identifier; local_arxiv, observed 2026-08-11T17:40:15.261910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b532f459-65ec-45f9-8d55-210b6830fe69 · outbound

This paper cites Policy augmentation: An exploration strategy for faster convergence of deep reinforcement learning algorithms,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Policy augmentation: An exploration strategy for faster convergence of deep reinforcement learning algorithms,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.614278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3c7762aa-c3e9-4b3f-a55b-0e43f75a2f81 · outbound

This paper cites Elasticface: Elastic margin loss for deep face recog- nition,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Elasticface: Elastic margin loss for deep face recog- nition,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.624702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 569e166b-5006-4b32-bd7d-83bbf0d5f3ab · outbound

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

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Reflection backdoor: A natural backdoor attack on deep neural networks,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.592212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d2b50273-8101-4757-a5dd-c3adc4351331 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Bert: Pre-training of deep bidirectional transformers for language understanding,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.603616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0ba27de2-9ba4-4495-bca9-65bac0e3c535 · outbound

This paper cites Universal adversarial attacks with natural triggers for text classification,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Universal adversarial attacks with natural triggers for text classification,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.570203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ed8b1fed-3cbf-4681-b1cd-d595c8671b85 · outbound

This paper cites Trojaning attack on neural networks,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Trojaning attack on neural networks,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.581083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5d35c576-7770-4963-99fb-78f25c67b2b4 · outbound

This paper cites Black-box backdoor defense via zero-shot image pu- rification,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Black-box backdoor defense via zero-shot image pu- rification,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.547941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e58b2ae2-a19b-4ac9-8a63-f0932afdfc02 · outbound

This paper cites a photo of.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images a photo of

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.646411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0ce26b1e-0115-407e-ab14-d2be157f0407 · outbound

This paper cites Minimal: mining models for universal adversarial triggers,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Minimal: mining models for universal adversarial triggers,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.559031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 951396ae-82f0-4c5b-b267-a1dc9658fef0 · outbound

This paper cites Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.001115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b77be1-ee5e-4ca4-a944-67898e6bdda7 · outbound

This paper cites Shared adver- sarial unlearning: Backdoor mitigation by unlearning shared adversarial examples,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Shared adver- sarial unlearning: Backdoor mitigation by unlearning shared adversarial examples,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.536668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c578902f-bed5-4141-9b12-e13841335cc4 · outbound

This paper cites Refit: a unified watermark removal framework for deep learning systems with limited data,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Refit: a unified watermark removal framework for deep learning systems with limited data,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.525804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 37efcf90-7ed9-420c-8e2a-8d43132f6fd5 · outbound

This paper cites Rab: Provable robustness against backdoor attacks,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Rab: Provable robustness against backdoor attacks,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.515081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4ace7181-3d4c-4904-816f-e75d4d5c7b81 · outbound

This paper cites Neural attention distillation: Erasing backdoor triggers from deep neural networks,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Neural attention distillation: Erasing backdoor triggers from deep neural networks,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.503304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8e1eda64-b39d-4918-8993-905a4b395661 · outbound

This paper cites One-shot neural backdoor erasing via adversarial weight masking,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images One-shot neural backdoor erasing via adversarial weight masking,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.490914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9c6002f0-e072-4897-92dd-0eb15186c3ce · outbound

This paper cites A simple unified framework for detecting out-of-distribution samples and adversarial attacks,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images A simple unified framework for detecting out-of-distribution samples and adversarial attacks,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.479212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4839a7f9-c0bb-4f58-82e1-6f0b03fe45fd · outbound

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

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.033559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baacadd0-cde0-4984-84c6-bead3314f34f · outbound

This paper cites Fast and lightweight vision- language model for adversarial traffic sign detection,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Fast and lightweight vision- language model for adversarial traffic sign detection,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.468088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e390fd01-283a-4658-8c9a-15e209887883 · outbound

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

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Bdetclip: Multimodal prompting contrastive test-time backdoor detection,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.041093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb880a1-7432-4cd1-adff-ef968124d5f8 · outbound

This paper cites Badnets: Evaluating backdooring attacks on deep neural net- works,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Badnets: Evaluating backdooring attacks on deep neural net- works,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.457388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c45120cc-1fe3-49d7-92ad-6ed4a55c99fd · outbound

This paper cites Learning transferable visual models from natu- ral language supervision,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Learning transferable visual models from natu- ral language supervision,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.445655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0d1b821a-099d-4d29-b694-6395847038b8 · outbound

This paper cites Robust physical-world attacks on deep learning visual classification,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Robust physical-world attacks on deep learning visual classification,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.052137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eb18d05-2695-4d34-b1ce-18c43e930d11 · outbound

This paper cites Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.428774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 72c7986d-5d8b-4820-a6c1-7b7e312fcf02 · outbound

This paper cites Deep residual learning for image recognition,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Deep residual learning for image recognition,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.059438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aa318fb-1d85-4c9b-8417-bb70bb0cf539 · outbound

This paper cites How Much Can CLIP Benefit Vision-and-Language Tasks?.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images How Much Can CLIP Benefit Vision-and-Language Tasks?

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.062784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bd396c6-3a54-4ad4-854c-7c70cbc43cd9 · outbound

This paper cites Learning to prompt for vision-language models,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Learning to prompt for vision-language models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.411306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 004e3bf3-21ea-4a24-84e7-2febb9eaef8f · outbound

This paper cites Conditional prompt learning for vision-language models,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Conditional prompt learning for vision-language models,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.399659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ed520110-1897-4d53-939f-9da5ea0323b3 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Adam: A Method for Stochastic Optimization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.073664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68534ce6-672c-4f3f-a4d6-5aab5765b247 · outbound

This paper cites Invisible backdoor attacks on deep neural networks via steganography and regularization,.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Invisible backdoor attacks on deep neural networks via steganography and regularization,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:40:15.386416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 961a9220-7ef2-4354-8a80-83a49b2d8ec7 · outbound

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

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Learning multiple layers of features from tiny images,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.081187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ac9eddc-6130-4777-9557-b70ca3cf314c · outbound

This paper cites Visualizing data using t-sne.

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Visualizing data using t-sne

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T17:40:15.084723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c23245d3-d15b-48ab-8ddf-2e1d352f9e6b · inbound