Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks | Paper Citation Record

Observation 00b5e9b5-7002-44a4-8515-5be0b96f5869 · outbound

This paper cites write newline.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.464754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 884a2cbc-5269-4c0d-9a27-563d874706a8 · outbound

This paper cites Fast and precise certification of transformers.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Fast and precise certification of transformers

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.747857Z

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.

Observation 05626bde-6126-4af8-940d-99cc5e5267b2 · outbound

This paper cites Mitigating backdoor attacks in lstm-based text classification systems by backdoor keyword identification.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Mitigating backdoor attacks in lstm-based text classification systems by backdoor keyword identification

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.735504Z

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.

Observation 6d3c4d2f-86ab-430a-8e9d-933ba343c448 · outbound

This paper cites Badpre: Task-agnostic backdoor attacks to pre-trained nlp foundation models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Badpre: Task-agnostic backdoor attacks to pre-trained nlp foundation models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.722812Z

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.

Observation e9278386-e483-489c-80da-47fda6bd9fe7 · outbound

This paper cites Badnl: Backdoor attacks against nlp models with semantic-preserving improvements.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Badnl: Backdoor attacks against nlp models with semantic-preserving improvements

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.709445Z

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.

Observation 9629dbfd-dbda-4a14-80c3-e44b9020ba17 · outbound

This paper cites SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.541222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 832a48f5-471a-4f4c-a4fa-9c27204f8b82 · outbound

This paper cites Certified adversarial robustness via randomized smoothing.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Certified adversarial robustness via randomized smoothing

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.694625Z

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.

Observation ca2e0958-0fe7-4ac6-a5af-b95f8d0dfb07 · outbound

This paper cites A unified evaluation of textual backdoor learning: Frameworks and benchmarks.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks A unified evaluation of textual backdoor learning: Frameworks and benchmarks

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.679405Z

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.

Observation 16fe3508-ab75-4d9d-9e7f-bebfecd268fd · outbound

This paper cites A backdoor attack against lstm-based text classification systems.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks A backdoor attack against lstm-based text classification systems

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.664833Z

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.

Observation 2896a4dd-9186-4c32-8c6b-358bd37bf600 · outbound

This paper cites A technique for computer detection and correction of spelling errors.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks A technique for computer detection and correction of spelling errors

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.649563Z

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.

Observation 780808f4-5df8-40ca-a838-476059a68f61 · outbound

This paper cites Cert-rnn: Towards certifying the robustness of recurrent neural networks.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Cert-rnn: Towards certifying the robustness of recurrent neural networks

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.635212Z

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.

Observation 857776c4-4c6f-40bb-a74d-1561a1080c84 · outbound

This paper cites The Llama 3 Herd of Models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.569567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cdbece0-798b-45b8-bafb-8f6dccdad253 · outbound

This paper cites Large scale crowdsourcing and characterization of twitter abusive behavior.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Large scale crowdsourcing and characterization of twitter abusive behavior

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.620714Z

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.

Observation 086b7f21-dc21-4266-b1fd-21b27170c5cb · outbound

This paper cites Threats to Pre-trained Language Models: Survey and Taxonomy.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Threats to Pre-trained Language Models: Survey and Taxonomy

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:43:25.150435Z

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.

Observation 3e411604-3366-4934-b8c5-f215e8fd1170 · outbound

This paper cites Lora: Low-rank adaptation of large language models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Lora: Low-rank adaptation of large language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.584276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a547fe-ebfe-4a8c-a0e6-d794b9d9adef · outbound

This paper cites Achieving verified robustness to symbol substitutions via interval bound propagation.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Achieving verified robustness to symbol substitutions via interval bound propagation

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.598698Z

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.

Observation 54f4aaac-de99-42b2-9c0f-2bc31ad5c99f · outbound

This paper cites Advancing the Robustness of Large Language Models through Self-Denoised Smoothing.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Advancing the Robustness of Large Language Models through Self-Denoised Smoothing

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:43:25.115510Z

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.

Observation ae12e00d-ea79-494e-85aa-81333f7ef68c · outbound

This paper cites Certified robustness to adversarial word substitutions.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Certified robustness to adversarial word substitutions

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.585610Z

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.

Observation 5e65f38d-0fe5-4c2e-a7e8-eff9836236d1 · outbound

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

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Bert: Pre-training of deep bidirectional transformers for language understanding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.603206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a26346c7-3b24-420e-837b-3b67fef45327 · outbound

This paper cites On information and sufficiency.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks On information and sufficiency

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.608471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aefc3474-130d-440b-beb0-accfda82f06a · outbound

This paper cites Weight poisoning attacks on pretrained models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Weight poisoning attacks on pretrained models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.554084Z

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.

Observation 49884ec4-54c4-4ca1-9ac0-55de99c695e8 · outbound

This paper cites Newsweeder: Learning to filter netnews.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Newsweeder: Learning to filter netnews

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.541079Z

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.

Observation e813bb58-9554-4180-9662-d1cf73d572bb · outbound

This paper cites Binary codes capable of correcting deletions, insertions, and reversals.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Binary codes capable of correcting deletions, insertions, and reversals

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.526316Z

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.

Observation 34a395a6-78b0-4103-bc92-f34eddb0cc9d · outbound

This paper cites Backdoor attacks on pre-trained models by layerwise weight poisoning.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Backdoor attacks on pre-trained models by layerwise weight poisoning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.512518Z

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.

Observation 1e5c96f4-00c3-424a-957d-947d1ccbca33 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.722282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1faaf594-1bac-4127-80a3-f1cf098259c3 · outbound

This paper cites CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:43:24.996083Z

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.

Observation 2c6a231b-1378-4320-ab9f-df3ac7dbb173 · outbound

This paper cites Learning word vectors for sentiment analysis.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Learning word vectors for sentiment analysis

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.730657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d64ae5-bd58-4378-aa97-f3fab945aa9c · outbound

This paper cites TextGuard: Provable Defense against Backdoor Attacks on Text Classification.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks TextGuard: Provable Defense against Backdoor Attacks on Text Classification

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.734540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce8d0e1-86dd-4534-913b-d6fbafb34918 · outbound

This paper cites Onion: A simple and effective defense against textual backdoor attacks.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Onion: A simple and effective defense against textual backdoor attacks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.489060Z

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.

Observation 439096aa-d2f3-4455-8e14-1b1421c35e09 · outbound

This paper cites Hidden killer: Invisible textual backdoor attacks with syntactic trigger.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Hidden killer: Invisible textual backdoor attacks with syntactic trigger

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.475274Z

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.

Observation 9db24ed0-d71b-4569-8053-8319ed37d858 · outbound

This paper cites Turn the combination lock: Learnable textual backdoor attacks via word substitution.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Turn the combination lock: Learnable textual backdoor attacks via word substitution

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.461082Z

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.

Observation 9aabcf6a-0f9a-42bb-9e42-73a0bb4880e2 · outbound

This paper cites Backdoor pre-trained models can transfer to all.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Backdoor pre-trained models can transfer to all

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.447182Z

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.

Observation 684207f7-bd1b-4b28-87be-30c75f977459 · outbound

This paper cites Recursive deep models for semantic compositionality over a sentiment treebank.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Recursive deep models for semantic compositionality over a sentiment treebank

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.753109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c00b0cff-6406-42c6-95b9-50a1ffd0ad04 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.756804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21363a7f-fb8d-4ebe-bcaf-c17ed3734b21 · outbound

This paper cites On Certifying Robustness against Backdoor Attacks via Randomized Smoothing.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.760660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af410a92-0d88-4efb-9e82-a72659142b81 · outbound

This paper cites Certified robustness to word substitution attack with differential privacy.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Certified robustness to word substitution attack with differential privacy

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.424046Z

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.

Observation e4a46545-b3ab-4206-a9b9-627614bec2c9 · outbound

This paper cites Robustness-aware word embedding improves certified robustness to adversarial word substitutions.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Robustness-aware word embedding improves certified robustness to adversarial word substitutions

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.411043Z

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.

Observation 6d0c6798-2cd9-492c-af33-9001e0993add · outbound

This paper cites Rab: Provable robustness against backdoor attacks.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Rab: Provable robustness against backdoor attacks

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.397293Z

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.

Observation e901b5e5-8850-43cf-96d6-25b78cdfb22d · outbound

This paper cites Crfl: Certifiably robust federated learning against backdoor attacks.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Crfl: Certifiably robust federated learning against backdoor attacks

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.382529Z

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.

Observation f1c083b1-3d8a-46d8-ad83-53539a500937 · outbound

This paper cites Bite: Textual backdoor attacks with iterative trigger injection.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Bite: Textual backdoor attacks with iterative trigger injection

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.369558Z

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.

Observation 0129ba34-744a-41fa-bba1-c019629a5c5d · outbound

This paper cites Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in nlp models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in nlp models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.356571Z

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.

Observation c24c7006-fbb2-44cc-98b1-c7805e3b2b88 · outbound

This paper cites Rap: Robustness-aware perturbations for defending against backdoor attacks on nlp models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Rap: Robustness-aware perturbations for defending against backdoor attacks on nlp models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.343464Z

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.

Observation 811005e4-7fe7-4210-9458-ea841acffe84 · outbound

This paper cites Safer: A structure-free approach for certified robustness to adversarial word substitutions.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Safer: A structure-free approach for certified robustness to adversarial word substitutions

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.330625Z

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.

Observation a5dc6609-2195-4df4-8cbb-249103a48e5e · outbound

This paper cites Semeval-2019 task 6: Identifying and categorizing offensive language in social media (offenseval).

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Semeval-2019 task 6: Identifying and categorizing offensive language in social media (offenseval)

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.802925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 312e2345-2fdd-4ac1-a6ec-d2dfff4e45a6 · outbound

This paper cites Certified robustness to text adversarial attacks by randomized [mask].

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Certified robustness to text adversarial attacks by randomized [mask]

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.303495Z

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.

Observation cef4db56-48d3-448c-8242-a6debb71f720 · outbound

This paper cites Character-level convolutional networks for text classification.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Character-level convolutional networks for text classification

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.812581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49ca8bee-c2a5-46fd-bc8a-bd6a496d897d · outbound

This paper cites Trojaning language models for fun and profit.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Trojaning language models for fun and profit

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.278331Z

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.

Observation ede714ba-3973-4aae-a2d4-751813776b43 · outbound

This paper cites Text-crs: A generalized certified robustness framework against textual adversarial attacks.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Text-crs: A generalized certified robustness framework against textual adversarial attacks

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.263857Z

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.

Observation 6f1040fc-9eb7-41ed-85cb-73dbaae08c25 · outbound

This paper cites Random smooth-based certified defense against text adversarial attack.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Random smooth-based certified defense against text adversarial attack

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.247916Z

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.

Observation bdf6d03d-f83b-47cf-8651-1ae4ad5df79f · outbound

This paper cites Certified Robustness for Large Language Models with Self-Denoising.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Certified Robustness for Large Language Models with Self-Denoising

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.830390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e2492d-6065-447b-a01a-6db1d943f88e · outbound

This paper cites Certified robustness against natural language attacks by causal intervention.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Certified robustness against natural language attacks by causal intervention

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.228939Z

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.

Observation 9909c6b8-19a9-45bd-92c7-d908ade9326e · outbound

This paper cites Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.844859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc981d4-ce1b-4f45-9926-d7fe02f2ad0f · outbound

This paper cites Moderate-fitting as a natural backdoor defender for pre-trained language models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Moderate-fitting as a natural backdoor defender for pre-trained language models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:43:25.214058Z

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.

Observation 3e495699-67c5-4fed-b617-b36584aed68a · outbound

This paper cites @esa (Ref.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks @esa (Ref

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.852617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3539ce4e-c4ef-42ed-bbd3-eccf26facc59 · outbound

This paper cites an unresolved cited work.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.856921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce4d46fb-e9dc-4ef1-820f-3fe58b5014c4 · outbound

This paper cites Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models.

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T17:43:24.861099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers