Pith. sign in

Paper Citation Record · LEDGER

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness

As of 10 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 0 inbound Pith citation observations for arXiv:2606.06938.

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

pith.paper-citation-record.v1
2606.06938 v1

Coverage vector

measured 94 of 94 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T22:27:55.156434Z

measured 94 of 94 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

94 of 94 outbound references displayed

  • verified exact3
  • verified fuzzy0
  • unresolved91
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 722dc427-86b0-4498-974e-c506ba423f3d · outbound

This paper cites Combating adver- saries with anti-adversaries.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Combating adver- saries with anti-adversaries

Reference 1

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:de2a5de3289ffd1de3f2c965a4cd4f259bb6607d4d386f069ef977939686cd75

Observation d027da7a-6edc-4eb9-8156-3109333404ba · outbound

This paper cites Square attack: a query-efficient black-box adversarial attack via random search.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Square attack: a query-efficient black-box adversarial attack via random search

Reference 2

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a57af2f739e17e4a2ca68d5c4708cb7c0c6c07ffe1cc506f09ea3b6503910571

Observation 6d47d076-977f-49c2-81ef-e5d2d0e99045 · outbound

This paper cites Obfus- cated gradients give a false sense of security: Circumventing defenses to adversarial examples.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Obfus- cated gradients give a false sense of security: Circumventing defenses to adversarial examples

Reference 3

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:72dee4517203362018cb851a2b7a0b087a146bc832de297dc848f3828b1bc96a

Observation b5753ccc-fffc-48fe-babf-343e613cfcab · outbound

This paper cites Synthesizing robust adversarial examples.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Synthesizing robust adversarial examples

Reference 4

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:0e0ed76cf9de576172be2e155e2deb7a427fc34fe3b9f1efa008c5095680d871

Observation 65d9f12f-fab3-4813-9744-49547b051a23 · outbound

This paper cites Recent advances in adversarial training for adversarial ro- bustness.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Recent advances in adversarial training for adversarial ro- bustness

Reference 5

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:26e3fefbae4949b983ecaf70b597d9815a9f673d1624f160ac6d55a61150b1fc

Observation 20837a54-6bc2-45be-9034-49fade6f232f · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 6

Resolution
verified exact
local_arxiv, observed 2026-07-02T16:37:09.667762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:b5080203b271ef7b6615d3bf53e70184fa692d3a16c9e71ddb5d3a980822e20c

Observation ac6fb67a-59b3-4b4a-b943-9720699ee42c · outbound

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

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Food-101–mining discriminative components with random forests

Reference 7

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:65499833fffde4420cc2e8783387ca404d7bf630719f87f26ac52836d4f06324

Observation 660fb34a-fe02-4d7d-b19c-c2152484c503 · outbound

This paper cites Towards evaluating the robustness of neural networks.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Towards evaluating the robustness of neural networks

Reference 8

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:08a3ed71b7887928337e373fad9bbfc87234a3a5b9e1b06bca498209baacc478

Observation e6ba3083-1249-4ade-92bc-0ca6d56f1df9 · outbound

This paper cites Multi-cache enhanced prototype learning for test- time generalization of vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Multi-cache enhanced prototype learning for test- time generalization of vision-language models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a98916970d315ea406e48f7347a4635ed941ca81067647e4aabda7c730160828

Observation 75ca99d6-c76e-49e7-bc2a-ff76080f6a14 · outbound

This paper cites Describing textures in the wild.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Describing textures in the wild

Reference 10

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:ca7c2ae299129a1f77ad72318f6f00dc0c673bd84d20316fa9243410acc1ea15

Observation 88bd87ec-c326-4f9c-a684-b0bbbe485367 · outbound

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

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness An analysis of single-layer networks in unsupervised feature learning

Reference 11

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:867ad848b4580af560b89057b160ff991d4c3013ccf1aefb3f8c3f0271f445ac

Observation 93a8f72c-ed29-4f89-834f-2de884fce3f6 · outbound

This paper cites Certified adversarial robustness via randomized smoothing.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Certified adversarial robustness via randomized smoothing

Reference 12

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a451011576053a4b077ebe986ddeace645ae7a49352326fbb9672f8709427eb6

Observation 1840c40c-a5e7-4726-8508-a9fbee8c8449 · outbound

This paper cites Reliable evalua- tion of adversarial robustness with an ensemble of diverse parameter-free attacks.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Reliable evalua- tion of adversarial robustness with an ensemble of diverse parameter-free attacks

Reference 13

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:329bf4f12a1ca7348b5abb9eb884428a82c664e6dbe0ef06afdfa60436c9901d

Observation 26cd9629-7771-4a3e-9fa7-8d97e7ffdf1e · outbound

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

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Imagenet: A large-scale hierarchical image database

Reference 14

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:332d3114865e60675b9b4a599cdef40178ae08c0c73e846998f4a4370c2c6aa4

Observation 2b4b4304-cbcb-4e76-b6fa-f00de421ffef · outbound

This paper cites Learning gener- ative visual models from few training examples: An incre- mental bayesian approach tested on 101 object categories.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Learning gener- ative visual models from few training examples: An incre- mental bayesian approach tested on 101 object categories

Reference 15

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a24710d38c779eac2d38fda534391a17bf05dabd6acbe70f7ddc5b0ae4601129

Observation c32c9502-86ab-4a73-9342-27c56b417d8e · outbound

This paper cites Explaining and harnessing adversarial examples.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Explaining and harnessing adversarial examples

Reference 16

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:fecabd6287250e237c117ab4e9b066528aa2851e44af64210e8918a8636c3543

Observation d6e2a9c9-9907-4131-92bb-2a1191c69c7f · outbound

This paper cites Caltech- 256 object category dataset.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Caltech- 256 object category dataset

Reference 17

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:978a4f93b086b04e95e89a2556875f568c68924e154ba3df92a1e8bf9fb1bff1

Observation 22098acc-ec98-4ff3-80f9-42b3a7592c96 · outbound

This paper cites an unresolved cited work.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Unresolved cited work

Reference 18

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:b35dae085bb69ab13cf28d4a9208526cc243690ada9e68a433949400c9fc7252

Observation fcc8d42a-ff29-477a-a5a9-b52a7293811c · outbound

This paper cites Augmix: A simple data processing method to improve robustness and uncertainty.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Augmix: A simple data processing method to improve robustness and uncertainty

Reference 19

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:9578f8d884b273db94b41f6009e6c64d9f9202cb0e4a09e4686910a1dde0a324

Observation 2e48862a-dff7-4842-b1d3-e954847be5e3 · outbound

This paper cites The many faces of robust- ness: A critical analysis of out-of-distribution generalization.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness The many faces of robust- ness: A critical analysis of out-of-distribution generalization

Reference 20

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:822d5d78ce207e9b6b7ec49fea8c54143cf091d31d48170c8ea2a32f752d93bc

Observation 891e51e2-4cd9-4b3b-9a1e-de43226417c5 · outbound

This paper cites Natural adversarial examples.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Natural adversarial examples

Reference 21

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:5ccb2e079f6e9222cf1a89f385b18487230715cf337bdc16ece55d55ca11ec41

Observation 14442515-8658-4689-acee-c62fcf120426 · outbound

This paper cites Cosmic: Clique- oriented semantic multi-space integration for robust clip test- time adaptation.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Cosmic: Clique- oriented semantic multi-space integration for robust clip test- time adaptation

Reference 22

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:7ad14686f2013db30c6486abb4dfae5467cff0f7c24e9db3c89342dc6eee428f

Observation 2c514950-900a-43ea-b74e-c4c246f221fd · outbound

This paper cites Black-box adversarial attacks with limited queries and information.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Black-box adversarial attacks with limited queries and information

Reference 23

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:d29cc5a24ea7e7f3fdad633fca144e217c197b58f43c27571a30cbbc6f30f5a8

Observation 7a3dd0b9-cca0-455f-8127-bf9ac39705d5 · outbound

This paper cites Test-time prompt tuning for zero-shot depth comple- tion.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Test-time prompt tuning for zero-shot depth comple- tion

Reference 24

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:86e9dc63fc9a3d7eb0fe49e41f454b1545828ee12653985d30e695cc1422c4a8

Observation c6189478-c717-4a08-a8a7-77ba3affb691 · outbound

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

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Scaling up visual and vision-language representation learning with noisy text supervision

Reference 25

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:d1c71f48df850d072b48f6159446b9da9957966b6fb35749c106b868b45e56af

Observation 31a39e4e-07e0-4878-8b85-f39fd5549e9a · outbound

This paper cites Efficient test-time adaptation of vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Efficient test-time adaptation of vision-language models

Reference 26

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:e84380e72f5770ecbd2bef9872a8137cc9f96e1d74daaf044849904ae3459a9e

Observation a7d65593-0508-4651-9476-d791a8c8579d · outbound

This paper cites Swag-net: Semantic word-aware graph network for temporal video grounding.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Swag-net: Semantic word-aware graph network for temporal video grounding

Reference 27

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:c034be12dfed475f8f2c70b6c300b17a24e8f95e0591f36dabafa82d431271a1

Observation 2d51bd3b-0abd-44d3-ba77-47d22cd00062 · outbound

This paper cites Gaussian mixture proposals with pull- push learning scheme to capture diverse events for weakly supervised temporal video grounding.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Gaussian mixture proposals with pull- push learning scheme to capture diverse events for weakly supervised temporal video grounding

Reference 28

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:4ae2601c4ba29e6c0f485a5e2fb795d54b8cc6488eb12b0ec4d1b2b1a21b26fd

Observation 745aa5cc-9a96-444b-a4d5-3b4ae523b134 · outbound

This paper cites Learnable negative proposals using dual-signed cross- entropy loss for weakly supervised video moment localiza- tion.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Learnable negative proposals using dual-signed cross- entropy loss for weakly supervised video moment localiza- tion

Reference 29

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:99db8222f03e6dbaf5d5712005bbed3669c53fde833456533ed36b3085b1c722

Observation 98b9e090-231c-4981-8108-a896861c9ead · outbound

This paper cites Finding opti- mal video moment without training: Gaussian boundary op- timization for weakly supervised video grounding.IEEE Transactions on Multimedia, 2026.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Finding opti- mal video moment without training: Gaussian boundary op- timization for weakly supervised video grounding.IEEE Transactions on Multimedia, 2026

Reference 30

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:d0297f3bce356d56ab89566f506d1ae6e969acf7c9ce275175ac81b55bdaf8da

Observation 4c200ec4-6d20-4d8c-a880-85b4257d6c52 · outbound

This paper cites 3d object representations for fine-grained categorization.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness 3d object representations for fine-grained categorization

Reference 31

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:59e631d9987880dea10bbb3f84bc5aa4d73802d6c5b206ead718c200117ed391

Observation 134a55dc-d3fa-4a05-97f7-cfdf95212b52 · outbound

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

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Learning multiple layers of features from tiny images

Reference 32

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:818ada662baf6ec6e476ccdf5535aa8423c001700b27b1e11589ecca35fad697

Observation cc6c2cf1-a544-4c7d-b711-2abacfdab084 · outbound

This paper cites Ad- versarial examples in the physical world.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Ad- versarial examples in the physical world

Reference 33

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:03e94e0ff3b23107c183d78e1eb56143f39e3fcbb490e53735b619aedfcb37d8

Observation 21000688-322c-4df8-8908-b1b29630ec50 · outbound

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

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness One prompt word is enough to boost adversarial robustness for pre-trained vision-language models

Reference 34

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:3bd3ef2b1d3217518d28f8d4b49eec76663a506ad44c49235df7d8ebc7c20f1e

Observation 097707a5-f5ea-45b4-957b-d2acfb448a9d · outbound

This paper cites Language-driven anchors for zero-shot ad- versarial robustness.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Language-driven anchors for zero-shot ad- versarial robustness

Reference 35

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:087ed561190023295a37ccd4a2b3962300b5a372ae58200539ed7d09172943b0

Observation 5d444e05-8be7-45ff-bee5-430f6bd6619c · outbound

This paper cites Visual instruction tuning.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Visual instruction tuning

Reference 36

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:2e3908d4429105941ee0589617ee11962a41d2715082911e872f6a602f9a3e4a

Observation 1f3d7006-3d6c-464e-98f7-ae562de2f05c · outbound

This paper cites Visualiz- ing data using t-sne.Journal of machine learning research,.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Visualiz- ing data using t-sne.Journal of machine learning research,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:5c53f31c8bab2e9736650454019b03796b3238f5f2cfe61d88e0bc4a04906f23

Observation aa7520da-c393-4dbd-9b72-22beaef4c5be · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Towards deep learning models resistant to adversarial attacks

Reference 38

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:179b379cab673a1f20fa6daaee55bdc03a21c30ce17e9ac83470f5eeb805f182

Observation a7bf321a-132e-4557-b8c5-fcc17010d601 · outbound

This paper cites Fine-Grained Visual Classification of Aircraft.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Fine-Grained Visual Classification of Aircraft

Reference 39

Resolution
verified exact
local_arxiv, observed 2026-07-02T16:37:09.662117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:d21ed4e44bedc43fee0deeabbed6cc4d58a223a23c5c05a677fa959d611dc739

Observation b721339b-cc49-424f-897e-7c980aa75fe7 · outbound

This paper cites Understanding zero-shot adversarial robust- ness for large-scale models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Understanding zero-shot adversarial robust- ness for large-scale models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a0735d0b6d7fb274f78f58ad9d957674bf6ee0258f0801932c923dfd93635bef

Observation ec5ba848-94b7-4ddb-89bd-899518ba0527 · outbound

This paper cites Deepfool: a simple and accurate method to fool deep neural networks.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Deepfool: a simple and accurate method to fool deep neural networks

Reference 41

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:2291ed77598c29370b00911b7ce4bc2063e736bbb0a062ecfe2ecfbe0c838ec5

Observation e11a6a83-9fc3-49c0-98a0-1bb34ddb2837 · outbound

This paper cites Universal adversarial perturba- tions.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Universal adversarial perturba- tions

Reference 42

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:1c13dd905de25cbca77c801ed5de65c44b761ced2374ec09aec5282220be5feb

Observation a385eb9c-2991-45f4-ab01-0bb14021b7dc · outbound

This paper cites Diffusion models for ad- versarial purification.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Diffusion models for ad- versarial purification

Reference 43

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:eba055e070044d949ae210cc7d6de81ebd2488410281a88c89e7f8192f8cd9ea

Observation 57787c88-18ab-482e-831d-40bdd5aaec4e · outbound

This paper cites Automated flower classification over a large number of classes.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Automated flower classification over a large number of classes

Reference 44

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:cd79a9b74c2012d744e369a250e01547ab82d79ff80df9b77ea8320d33981a84

Observation 5205ac8a-b03f-44f1-88ba-e48d362334d7 · outbound

This paper cites The limitations of deep learning in adversarial settings.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness The limitations of deep learning in adversarial settings

Reference 45

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:3dbb70438c5afcc88fa8f59990eb19514dd51455f7310c4d5f637c0618601fc2

Observation 5abee188-dbc8-4b0f-ba6b-45d08d59892a · outbound

This paper cites Cats and dogs.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Cats and dogs

Reference 46

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:304ade06aaf686abd37a85cca17bbcdb063bb0888d9a8681bee85b969dd69346

Observation e17ea319-2009-4f8e-8a19-fe3d54be3f5f · outbound

This paper cites Enhancing adversarial robustness via test-time transforma- tion ensembling.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Enhancing adversarial robustness via test-time transforma- tion ensembling

Reference 47

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:8bcfd69b897d375db28333bd30eab5ea41423eacebc345473bd1d03cf795cb3f

Observation 476ef3d7-8742-4645-b664-b489bd6460b8 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Learn- ing transferable visual models from natural language super- vision

Reference 48

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:1ffe3468d908bf9fffa90b7af4db4d70710aa8b309d708f8e2e7ecdec2d60083

Observation d42dcaf4-d8be-4fc6-aa3d-c0e4fe6a5a6f · outbound

This paper cites Zero-shot text-to-image generation.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Zero-shot text-to-image generation

Reference 49

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:bf259c28b9ed0c474bcb4c7d1f8c5c551c8f62359c81e8101d61d7d784641f6f

Observation 6d6c8a66-e140-495b-a8d1-5b53464477b3 · outbound

This paper cites Do imagenet classifiers generalize to im- agenet? InICML, 2019.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Do imagenet classifiers generalize to im- agenet? InICML, 2019

Reference 50

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:88695bbdddd05cce32aa81abdc81d27ded437e4eab78bb27f00a889dbaad03b2

Observation d1f06aa8-e9a5-4e6c-adf6-25346cac315d · outbound

This paper cites Overfitting in ad- versarially robust deep learning.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Overfitting in ad- versarially robust deep learning

Reference 51

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:58c9924a6566d0f2eb56215c0ed65c9c1a14d624771d1c2bdef3e1608ac01722

Observation c6108851-58e6-4027-9640-734e1931f910 · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Photorealistic text-to-image diffusion models with deep language understanding

Reference 52

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:fb119e6816762d2c94dc0a013e51035ea8f8909b455d223f8a6cd657952c3a4c

Observation d87f85f0-ba07-47bc-88b7-e87676d570fd · outbound

This paper cites Provably robust deep learning via adversarially trained smoothed clas- sifiers.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Provably robust deep learning via adversarially trained smoothed clas- sifiers

Reference 53

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a4cfc4683d8cb7b6a3e68e9d079729b96b9caf9d95d1f672f340085c3443a839

Observation 0cf6b6cc-082d-4554-a587-d0086feda409 · outbound

This paper cites Denoised smoothing: A provable defense for pretrained classifiers.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Denoised smoothing: A provable defense for pretrained classifiers

Reference 54

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a4578418d2126eae3c07d5bdabb6fddc70ba7bc8883758b54a29f88a9845097f

Observation 7676b41b-9138-428b-9697-4ea867622902 · outbound

This paper cites Defense-gan: Protecting classifiers against adversarial at- tacks using generative models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Defense-gan: Protecting classifiers against adversarial at- tacks using generative models

Reference 55

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:cb69cba1c9752f08614cf65010c330f7fdac94a8c017d275e42c264a44bdde67

Observation 5da7503b-424a-416a-8c9e-3ddcc5b3dbd9 · outbound

This paper cites Robust clip: Unsupervised ad- versarial fine-tuning of vision embeddings for robust large vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Robust clip: Unsupervised ad- versarial fine-tuning of vision embeddings for robust large vision-language models

Reference 56

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:8f5d581d3cdeb7801ab849159926cbf6769a4f1baadf06ced9616916593f460f

Observation 96879c3c-e5a7-4864-b349-095da9885761 · outbound

This paper cites Improving robustness against common corruptions by covariate shift adaptation.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Improving robustness against common corruptions by covariate shift adaptation

Reference 57

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:376d9be72629ea9bcd13f19dbe050e8a0fcbc534759766903d9c4eb8161b9616

Observation 192ead39-5c0a-412c-944e-b823ffe3d251 · outbound

This paper cites Adversarial training for free! InNeurIPS, 2019.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Adversarial training for free! InNeurIPS, 2019

Reference 58

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:24ca6f45eaf31204408580f82ae48878a2b60ce4838e91886b5f9b9b9a91e185

Observation aa46e930-0050-4eec-8763-8135e65198bd · outbound

This paper cites O-tpt: Orthogonality constraints for calibrating test-time prompt tuning in vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness O-tpt: Orthogonality constraints for calibrating test-time prompt tuning in vision-language models

Reference 59

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:1f8a81470b32f241067c9743a358f1261d7ed92d61c8b385f12704fe2ce5135f

Observation b0189979-1435-48ad-8c70-a5bf5f6a92ab · outbound

This paper cites Jail- break in pieces: Compositional adversarial attacks on multi- modal language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Jail- break in pieces: Compositional adversarial attacks on multi- modal language models

Reference 60

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:8271f246ee800ae624aa665f12c8f152b45d6e380696e6d54e044dcd3afe6f22

Observation 7562e373-cbb5-4c3b-a54e-f889ee75eb90 · outbound

This paper cites R-tpt: Improving adversarial robustness of vision-language models through test-time prompt tuning.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness R-tpt: Improving adversarial robustness of vision-language models through test-time prompt tuning

Reference 61

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:24b74bb5bc6bec0782233d1a4bd31d867ddee47872c8a2c0b4c1f04539e003dc

Observation fec00b0f-b352-4c11-95d7-e773618aa7c5 · outbound

This paper cites Test- time prompt tuning for zero-shot generalization in vision- language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Test- time prompt tuning for zero-shot generalization in vision- language models

Reference 62

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:2283ef45227f9aeb8cb400cf828d57014caf123966d34ec5242039f02eb01f6c

Observation f2a5226f-32e5-49e1-81e0-d66fb00bb3c3 · outbound

This paper cites Clip models are few-shot learners: Empirical studies on vqa and visual entailment.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Clip models are few-shot learners: Empirical studies on vqa and visual entailment

Reference 63

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:bc37dff96b747fa721970c9225e3a63a611a32e0f3e05ccf01edd5f05fae103a

Observation f6074b01-5520-4059-b593-e2b7284f19fd · outbound

This paper cites A dataset of 101 human action classes from videos in the wild.Center for Research in Computer Vision, 2012.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness A dataset of 101 human action classes from videos in the wild.Center for Research in Computer Vision, 2012

Reference 64

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:af31ea05a35660b19b7632c02d3ec6061001a370ef569cd68fb8af81daf8a3b2

Observation 23e1ba3a-4a6d-4630-9dd6-fca1666e0254 · outbound

This paper cites One pixel attack for fooling deep neural networks.IEEE Transactions on Evolutionary Computation, 2019.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness One pixel attack for fooling deep neural networks.IEEE Transactions on Evolutionary Computation, 2019

Reference 65

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:6c605c328523d811c326e4da2a04e68093e3710d078a2515fa385228434cdaf9

Observation 5b3ac568-e2f3-4938-aa8f-d25bcd4135dc · outbound

This paper cites Test-time training with self- supervision for generalization under distribution shifts.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Test-time training with self- supervision for generalization under distribution shifts

Reference 66

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:07230e99a547aa2e3cd2b99cfd681063c483b54aa8a4e7c4c201af1bd26139a9

Observation 9408dd0b-5a47-4881-bace-c31207207cef · outbound

This paper cites In- triguing properties of neural networks.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness In- triguing properties of neural networks

Reference 67

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:1ea7f7f2175fff3c63c9f2ebbab9c4a1a622d5702335a17842b6ecd460f470ee

Observation e0a495a4-e047-45cb-9661-aeeab4da3645 · outbound

This paper cites Tesla: Test-time self-learning with au- tomatic adversarial augmentation.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Tesla: Test-time self-learning with au- tomatic adversarial augmentation

Reference 68

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:7c6f92124172dad3853662344e27dae516209736ffe9a005288c6c4136f6d697

Observation 5705fcf2-6209-41b6-949d-0d0aee1ee5e4 · outbound

This paper cites On the zero-shot adversarial robustness of vision-language models: A truly zero-shot and training-free approach.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness On the zero-shot adversarial robustness of vision-language models: A truly zero-shot and training-free approach

Reference 69

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:9d6782f5d929c4b08a3e9b91e66d754ff621eb685ef4bf42d763ae6b02f0cf64

Observation ee8e3c6b-dcb1-430b-b24d-5ee73bcb9f07 · outbound

This paper cites Tent: Fully test-time adaptation by entropy minimization.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Tent: Fully test-time adaptation by entropy minimization

Reference 70

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:e56e04695f7be9f24dc3d4dd0a5a80ef151a85991dc8de08f75b3d360ffee732

Observation d7fc2572-bfdb-45f7-bda8-300a0c8167e4 · outbound

This paper cites Learning robust global representations by penalizing local predictive power.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Learning robust global representations by penalizing local predictive power

Reference 71

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:7cb305344a3c35537fd71777a0f7cbb90f9e612ffd4dd96afd0d39be5e1b772d

Observation e5cca145-03a1-4be3-afb5-acee32ff0caa · outbound

This paper cites Con- tinual test-time domain adaptation.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Con- tinual test-time domain adaptation

Reference 72

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:1a540668d44741cce18114b99e4f797dae4244ed43a674434c6a8bb2e878c109

Observation d975bdfb-d6d9-40ea-a80b-3731e7331493 · outbound

This paper cites Pre- trained model guided fine-tuning for zero-shot adversarial robustness.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Pre- trained model guided fine-tuning for zero-shot adversarial robustness

Reference 73

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:51c65cd8a5c60ab679cb5812e25312304cfc913717c6d8c9dd71c32709b1125c

Observation cd7bc9d8-d19c-4987-a17d-5f9a90ae3ee3 · outbound

This paper cites Tapt: Test-time adversarial prompt tuning for robust inference in vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Tapt: Test-time adversarial prompt tuning for robust inference in vision-language models

Reference 74

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:5576d9baf043836a1188700041675392c130483016cea00f77c4a9d800c27baa

Observation 6df9f27e-dee0-4fd7-a116-c6e98654ad89 · outbound

This paper cites Fast is better than free: Revisiting adversarial training.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Fast is better than free: Revisiting adversarial training

Reference 75

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:3b831b535f112e78cb38f471064075ece87a52c9da9a836ac01c302620683cef

Observation 557b0c9d-2c97-45dc-a90e-25ff4097f3de · outbound

This paper cites Attacking Adversarial Attacks as A Defense.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Attacking Adversarial Attacks as A Defense

Reference 76

Resolution
verified exact
arxiv_id, observed 2026-07-02T16:37:09.665160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:e3f8866851d99feaa3c60f43f5973da91af76e2b25eb3b5b46d34b7e0657718c

Observation a6906326-8d1f-4013-aaf5-c5b496119235 · outbound

This paper cites Adversarial weight perturbation helps robust generalization.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Adversarial weight perturbation helps robust generalization

Reference 77

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:5392a9afc163ec47d246569c12fda023e56bf19e56f6dec075059160a6cf3147

Observation 3147a9a2-9458-45f1-b6f6-5e06e81e4d45 · outbound

This paper cites Sun database: Large-scale scene recognition from abbey to zoo.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Sun database: Large-scale scene recognition from abbey to zoo

Reference 78

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:1712e238be5433a7aaba587952cd35b09f32433a1b7903bb4e43400f42040e62

Observation 0ae7fcc4-18f0-4448-8f2a-9caebe4b57f3 · outbound

This paper cites Improving transferabil- 8 ity of adversarial examples with input diversity.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Improving transferabil- 8 ity of adversarial examples with input diversity

Reference 79

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:dc4cb17f640a6f187c632c56e0e1650c5b3a5969d52981a66a3a9b05462d0532

Observation 3e03ef9e-9ec7-4245-853b-0bfebb50e920 · outbound

This paper cites Chain of attack: On the robustness of vision-language models against transfer-based adversarial attacks.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Chain of attack: On the robustness of vision-language models against transfer-based adversarial attacks

Reference 80

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:e318e3c19b1605feaccb28c0a0ebd1fc95beab2fb4e54ac333d5bb291f92505d

Observation b25dc8fd-98ea-4f49-8dcd-b187aa34a257 · outbound

This paper cites Clip is strong enough to fight back: Test-time counterattacks to- wards zero-shot adversarial robustness of clip.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Clip is strong enough to fight back: Test-time counterattacks to- wards zero-shot adversarial robustness of clip

Reference 81

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:7ae05dfbee422df7761aa85a5eaed215dd36d091d562cdda8e7304954778b5db

Observation aa0075ed-5905-4a2b-80c7-0895a885773a · outbound

This paper cites Detclipv2: Scal- able open-vocabulary object detection pre-training via word- region alignment.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Detclipv2: Scal- able open-vocabulary object detection pre-training via word- region alignment

Reference 82

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:ddedd1b5cee46535c327c47d9472ea917dedead4e041c64149bf9970409d16bb

Observation a72feee5-dcd7-4679-9ff0-d9b6900b4666 · outbound

This paper cites Adversarial purification with score-based generative models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Adversarial purification with score-based generative models

Reference 83

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a69d7e95512ecb5bda09316468e3e100e52a8d222fd0afadea8dd5b7da67dd65

Observation 0e519c24-9d7e-42e5-86c4-43a6d569adc8 · outbound

This paper cites Coca: Contrastive captioners are image-text foundation models.Transactions on Machine Learning Research, 2022.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Coca: Contrastive captioners are image-text foundation models.Transactions on Machine Learning Research, 2022

Reference 84

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:4aa219baa53b85a1d1288c747793f1ad99cb6d9e83f33f7867b6f0275c30a570

Observation 0c7db467-1d87-419b-bd43-5d592c60e3b2 · outbound

This paper cites On the test-time zero- shot generalization of vision-language models: Do we really need prompt learning? InCVPR, 2024.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness On the test-time zero- shot generalization of vision-language models: Do we really need prompt learning? InCVPR, 2024

Reference 85

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:ebe3c8271e103aea024ac8f8bce940cdea6da3b2df5697d84a19f01744592bcc

Observation 8afa9940-36a2-4bc4-8b96-57f262376156 · outbound

This paper cites Theoretically principled trade-off between robustness and accuracy.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Theoretically principled trade-off between robustness and accuracy

Reference 86

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:8a66bc35749c368fdb3c6f2674a51fd67c129c5edaf690c7dbbc42cc2fec5114

Observation 8b397f23-3bd2-49ea-8feb-d33eaa8a999a · outbound

This paper cites Vision-language models for vision tasks: A survey.IEEE transactions on pattern analysis and machine intelligence,.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Vision-language models for vision tasks: A survey.IEEE transactions on pattern analysis and machine intelligence,

Reference 87

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:6b2126937469f3b34b6265c1e6eada2fbc275453695b14bf5adb1028742397fa

Observation fc265349-8aaa-4e8a-a3a1-42dffc368fc0 · outbound

This paper cites Adversarial prompt tuning for vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Adversarial prompt tuning for vision-language models

Reference 88

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:6579e6820eb87dbede4c88714fd7c42a3261a9d0374d6cd940066733533a9f34

Observation 299e0b61-2483-4276-a8bc-4c73e2a9ca26 · outbound

This paper cites Tip-adapter: Training-free clip-adapter for better vision- language modeling.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Tip-adapter: Training-free clip-adapter for better vision- language modeling

Reference 89

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:02c492bdc0d235dd5922f814651723c24201225a9db2acdc4ed7926ba5b76f82

Observation ed088b67-f7cf-4386-a2a5-af1f87c4a7b8 · outbound

This paper cites On evaluating adversarial robustness of large vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness On evaluating adversarial robustness of large vision-language models

Reference 90

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:45a0f230206e5f0e331bd3c6386b98e1536978aff63c1a150d21b998ac0e9e12

Observation c804a5f0-d14a-4510-8b30-35f9b5e2da23 · outbound

This paper cites Regionclip: Region-based language-image pretraining.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Regionclip: Region-based language-image pretraining

Reference 91

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:ff223913f0f1b3b2e020a2e30dfe6e663a902aaae35654d329bbc93a222ac692

Observation b34f5620-ff31-4fbd-b187-ff9310b86eba · outbound

This paper cites Bayesian test-time adaptation for vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Bayesian test-time adaptation for vision-language models

Reference 92

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:046a5ae047e47de3054063549c5a024830a59c9f912fd25b13874a55fee42f79

Observation 50879b66-0553-49b7-a21b-8417df33b541 · outbound

This paper cites Few-shot adversarial prompt learning on vision-language models.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Few-shot adversarial prompt learning on vision-language models

Reference 93

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:adee7ec3080a2cb5e3a004e7b53ca39e41779c5dd963952ba025e80911285803

Observation 68803f70-265b-4f14-9190-03ea39562f97 · outbound

This paper cites Enhancing clip robustness via cross-modality alignment.

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness Enhancing clip robustness via cross-modality alignment

Reference 94

Resolution
unresolved
no resolver link, observed 2026-06-27T22:27:55.156434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-27T22:27:55.156434Z digest=sha256:a6c60bb8e353f4d0d56da2fdc198e616a194a0ebcba82967a56e9c7fbb6b3769

Pith citing papers

No inbound Pith citation observations are available.