Paper Citation Record · LEDGER

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP

As of 10 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2601.19210.

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

pith.paper-citation-record.v1
2601.19210 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T07:47:37.615548Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

25 of 25 outbound references displayed

verified exact0
verified fuzzy0
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2ce0579b-5a7b-4051-bf5f-a5102ecf8b0f · outbound

This paper cites an unresolved cited work.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.615548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 741b3905-f467-4ee3-b63c-c8ce46d00e42 · outbound

This paper cites and Hwang, W.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP and Hwang, W

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.515585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cb44098-b36c-427b-b946-47a7c4f127d9 · outbound

This paper cites an unresolved cited work.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.520078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da6ce663-1381-4da2-a57b-edb21fe0b030 · outbound

This paper cites SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.524533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a46f1f1-a2dc-4ea3-a0ca-6dfd108e6f36 · outbound

This paper cites As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.529795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd4757c7-0b33-4dfe-bc5b-9880140fe3ab · outbound

This paper cites One prompt word is enough to boost adversarial robustness for pre- trained vision-language models.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP One prompt word is enough to boost adversarial robustness for pre- trained vision-language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.538971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a99661e-7213-41d0-afbd-c9fd42ce6490 · outbound

This paper cites DeepSeek-VL: Towards Real-World Vision-Language Understanding.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.543905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbe6cccd-ecce-4f2b-98ea-1e28c4c6c256 · outbound

This paper cites Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.549997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40761b31-ed6c-49cf-ab3a-d6e4f190b99e · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.554565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72af6f2a-8df6-46ce-a2a2-b384347b99aa · outbound

This paper cites an unresolved cited work.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.577260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25df41f2-ed47-49fe-b0ad-c51c755b6b34 · outbound

This paper cites Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.588939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70b264c-adf3-44c8-80dd-48a65e7ff2e2 · outbound

This paper cites 14 Section BTheoretical Analysis of Gradient Conflict.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP 14 Section BTheoretical Analysis of Gradient Conflict

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.594145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09335bfb-4d08-4a9d-bfef-ff00d7be1f6a · outbound

This paper cites To ad- dress black-box transferability, recent works predominantly leverage augmentation and cross-modal priors.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP To ad- dress black-box transferability, recent works predominantly leverage augmentation and cross-modal priors

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.600013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2a956d4-5893-41e4-a2b3-5a9c62e84298 · outbound

This paper cites an unresolved cited work.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.606536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dfa01e3-937b-4eda-93cc-9c243cc4e1fc · outbound

This paper cites Reading Isn't Believing: Adversarial Attacks On Multi-Modal Neurons.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Reading Isn't Believing: Adversarial Attacks On Multi-Modal Neurons

Reference 2008

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.568234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e2bcf1-0caa-42a9-88a9-9b7d190564b3 · outbound

This paper cites Fpt-noise: Dy- namic scene-aware counterattack for test-time adversar- ial defense in vision-language models.arXiv preprint arXiv:2510.20856,.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Fpt-noise: Dy- namic scene-aware counterattack for test-time adversar- ial defense in vision-language models.arXiv preprint arXiv:2510.20856,

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.496209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a9dc4c0-3c85-4a97-9877-90a4169b9c4e · outbound

This paper cites One perturbation is enough: On generating uni- versal adversarial perturbations against vision-language pre-training models.CoRR, abs/2406.05491,.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP One perturbation is enough: On generating uni- versal adversarial perturbations against vision-language pre-training models.CoRR, abs/2406.05491,

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.506205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab002be8-da6f-4a85-8bb6-475697dfdfe0 · outbound

This paper cites Fine-Grained Visual Classification of Aircraft.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Fine-Grained Visual Classification of Aircraft

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.559175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f929eb6-de4a-4e55-aee0-c83866fa4197 · outbound

This paper cites Attacking Adversarial Attacks as A Defense.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Attacking Adversarial Attacks as A Defense

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.583619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49bd0555-2734-4236-a374-51874690cb3c · outbound

This paper cites Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.534486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ec108bf-327e-4c1d-bf5a-317418b13b3d · outbound

This paper cites V- attack: Targeting disentangled value features for con- trollable adversarial attacks on lvlms.arXiv preprint arXiv:2511.20223,.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP V- attack: Targeting disentangled value features for con- trollable adversarial attacks on lvlms.arXiv preprint arXiv:2511.20223,

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.563725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf1b213c-57f8-43b4-912b-151de05a8023 · outbound

This paper cites ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.572696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1d7631d-f54d-427d-a6df-e24c31f22c16 · outbound

This paper cites How Robust is Google's Bard to Adversarial Image Attacks?.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP How Robust is Google's Bard to Adversarial Image Attacks?

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.500987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ffc59e0-12e5-4569-b6da-4a24c8690804 · outbound

This paper cites Learning generative visual models from few training examples: An incremen- tal bayesian approach tested on 101 object categories.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Learning generative visual models from few training examples: An incremen- tal bayesian approach tested on 101 object categories

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.510994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6feb0573-6c44-4cc8-84e6-a6bbe97e1899 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.490305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.