Confidence Elicitation: A New Attack Vector for Large Language Models | Paper Citation Record

Observation b06ff1ef-cc73-47e3-bf4c-128628083815 · outbound

This paper cites an unresolved cited work.

Confidence Elicitation: A New Attack Vector for Large Language Models Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.786466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d78a881-b929-4b82-b8f6-6469f15a48ef · outbound

This paper cites Choquette-Choo, Matthew Jagielski, Irena Gao, Pang Wei W Koh, Daphne Ippolito, Florian Tramer, and Ludwig Schmidt.

Confidence Elicitation: A New Attack Vector for Large Language Models Choquette-Choo, Matthew Jagielski, Irena Gao, Pang Wei W Koh, Daphne Ippolito, Florian Tramer, and Ludwig Schmidt

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.879718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 13509d42-e3dc-46ba-a3a4-e80328a353ef · outbound

This paper cites Universal Sentence Encoder.

Confidence Elicitation: A New Attack Vector for Large Language Models Universal Sentence Encoder

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.795141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f5518d8-9e12-4b3c-ab47-27144f0e0c99 · outbound

This paper cites Pappas, and Eric Wong.

Confidence Elicitation: A New Attack Vector for Large Language Models Pappas, and Eric Wong

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.799248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 698754f5-71db-40fe-9147-92c75dbee5aa · outbound

This paper cites Finetuning Language Models to Emit Linguistic Expressions of Uncertainty.

Confidence Elicitation: A New Attack Vector for Large Language Models Finetuning Language Models to Emit Linguistic Expressions of Uncertainty

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.802830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f747824e-f6cf-402f-841d-310002afad40 · outbound

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

Confidence Elicitation: A New Attack Vector for Large Language Models BERT : Pre-training of deep bidirectional transformers for language understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.806757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0105b3d3-142b-445d-940d-862a4c6102c8 · outbound

This paper cites Towards robustness against natural language word substitutions.

Confidence Elicitation: A New Attack Vector for Large Language Models Towards robustness against natural language word substitutions

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.861734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ff964c0e-4dec-4fd9-8d9e-96eef66c61f7 · outbound

This paper cites Towards Robustness Against Natural Language Word Substitutions.

Confidence Elicitation: A New Attack Vector for Large Language Models Towards Robustness Against Natural Language Word Substitutions

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-08T22:07:24.575044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 557450ae-0a2c-4b93-b625-7500fe980c65 · outbound

This paper cites H ot F lip: White-box adversarial examples for text classification.

Confidence Elicitation: A New Attack Vector for Large Language Models H ot F lip: White-box adversarial examples for text classification

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.817712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1878716a-2ee4-41ab-85b1-e5a46d1f514b · outbound

This paper cites o zde G \.

Confidence Elicitation: A New Attack Vector for Large Language Models o zde G \

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.850770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation faaf7918-2760-45d2-875d-41120c98f2c1 · outbound

This paper cites Special symbol attacks on nlp systems.

Confidence Elicitation: A New Attack Vector for Large Language Models Special symbol attacks on nlp systems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.824941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79102f9c-7e52-4b15-b45c-47f1a5845976 · outbound

This paper cites Using punctuation as an adversarial attack on deep learning-based NLP systems: An empirical study.

Confidence Elicitation: A New Attack Vector for Large Language Models Using punctuation as an adversarial attack on deep learning-based NLP systems: An empirical study

Reference 12

Resolution: verified exact; doi, observed 2026-08-08T22:06:39.243622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 554d9ae5-9e89-4a8d-8989-a237fb7c291d · outbound

This paper cites S em R o D e: Macro adversarial training to learn representations that are robust to word-level attacks.

Confidence Elicitation: A New Attack Vector for Large Language Models S em R o D e: Macro adversarial training to learn representations that are robust to word-level attacks

Reference 13

Resolution: verified exact; doi, observed 2026-08-08T22:07:24.840072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 651766c1-64e2-4ee2-a943-b1632ffd0f2a · outbound

This paper cites Reasoning robustness of LLM s to adversarial typographical errors.

Confidence Elicitation: A New Attack Vector for Large Language Models Reasoning robustness of LLM s to adversarial typographical errors

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.835312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 318cd17a-cb4b-4cbd-8a52-24675324cfeb · outbound

This paper cites Improving the robustness of question answering systems to question paraphrasing.

Confidence Elicitation: A New Attack Vector for Large Language Models Improving the robustness of question answering systems to question paraphrasing

Reference 15

Resolution: verified exact; doi, observed 2026-08-08T22:06:39.225930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1a62c797-d0f2-4036-abc4-36d2fa0c4b57 · outbound

This paper cites Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies.

Confidence Elicitation: A New Attack Vector for Large Language Models Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.841995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6a6f372-b76c-4e68-816c-a5f989fc19be · outbound

This paper cites Buelow, Rupert Langer, Bastian Dislich, Peter Boor, Volkmar Schulz, and Jakob Nikolas Kather.

Confidence Elicitation: A New Attack Vector for Large Language Models Buelow, Rupert Langer, Bastian Dislich, Peter Boor, Volkmar Schulz, and Jakob Nikolas Kather

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.829538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4bc83bd7-03db-49b4-bc60-21748889d076 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Confidence Elicitation: A New Attack Vector for Large Language Models Explaining and Harnessing Adversarial Examples

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.848950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67c9e2f2-fe89-4d1e-aafe-f34da834eaab · outbound

This paper cites Weinberger.

Confidence Elicitation: A New Attack Vector for Large Language Models Weinberger

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.820356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 23e68a1c-ffa6-40a4-bc1c-a6b263fae991 · outbound

This paper cites Weinberger.

Confidence Elicitation: A New Attack Vector for Large Language Models Weinberger

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.811122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 186e16d7-425a-4409-b80b-e489ede6ae96 · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

Confidence Elicitation: A New Attack Vector for Large Language Models Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.860489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b954e2-70f9-4fe4-8811-2180b2b28597 · outbound

This paper cites Adversarial example generation with syntactically controlled paraphrase networks.

Confidence Elicitation: A New Attack Vector for Large Language Models Adversarial example generation with syntactically controlled paraphrase networks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.864286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647e80db-2238-4247-b5ac-5712ba10c4ae · outbound

This paper cites Enhancing Adversarial Robustness of Vision-Language Models through Low-Rank Adaptation.

Confidence Elicitation: A New Attack Vector for Large Language Models Enhancing Adversarial Robustness of Vision-Language Models through Low-Rank Adaptation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.867893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a58d39df-2145-446f-9607-a5fde0f7adc7 · outbound

This paper cites an unresolved cited work.

Confidence Elicitation: A New Attack Vector for Large Language Models Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.871884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb3c12cf-08a3-4207-8db7-166d8ce8c966 · outbound

This paper cites How can we know when language models know? on the calibration of language models for question answering, 2021.

Confidence Elicitation: A New Attack Vector for Large Language Models How can we know when language models know? on the calibration of language models for question answering, 2021

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.794848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d6c5a754-7370-4648-884e-ba0ce5eb0735 · outbound

This paper cites Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment.

Confidence Elicitation: A New Attack Vector for Large Language Models Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.878882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9dbee5e-3d42-4649-9284-433a09178362 · outbound

This paper cites T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension.

Confidence Elicitation: A New Attack Vector for Large Language Models T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.882645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a369df4-247b-49f8-ba17-be4026cad235 · outbound

This paper cites Language models (mostly) know what they know, 2022.

Confidence Elicitation: A New Attack Vector for Large Language Models Language models (mostly) know what they know, 2022

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.886231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aebd11f4-4d22-4b0c-9f9f-f4a8ac384a84 · outbound

This paper cites Adversarial examples in the physical world.

Confidence Elicitation: A New Attack Vector for Large Language Models Adversarial examples in the physical world

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.889683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c3f464f-b1e8-4181-9921-8fb557c36dfd · outbound

This paper cites TextBugger : Generating adversarial text against real-world applications.

Confidence Elicitation: A New Attack Vector for Large Language Models TextBugger : Generating adversarial text against real-world applications

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.893679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60f91f8c-2ee1-48d2-b3f0-44a98023b594 · outbound

This paper cites BERT - ATTACK : Adversarial attack against BERT using BERT.

Confidence Elicitation: A New Attack Vector for Large Language Models BERT - ATTACK : Adversarial attack against BERT using BERT

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.897124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 539674aa-627c-4674-b010-3dab3568cdc1 · outbound

This paper cites Teaching models to express their uncertainty in words, 2022.

Confidence Elicitation: A New Attack Vector for Large Language Models Teaching models to express their uncertainty in words, 2022

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.778000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3dbed84e-2b53-4fa3-a8bf-19d53fac7d06 · outbound

This paper cites Sspattack: A simple and sweet paradigm for black-box hard-label textual adversarial attack.

Confidence Elicitation: A New Attack Vector for Large Language Models Sspattack: A simple and sweet paradigm for black-box hard-label textual adversarial attack

Reference 33

Resolution: verified exact; doi, observed 2026-08-08T22:06:39.187299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6d2cdb81-a076-488c-b72b-0b8d5f0ce0bd · outbound

This paper cites Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach.

Confidence Elicitation: A New Attack Vector for Large Language Models Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.908043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0863056b-d110-442d-911b-973bb4d2c7a9 · outbound

This paper cites Autodan: Generating stealthy jailbreak prompts on aligned large language models, 2024 b.

Confidence Elicitation: A New Attack Vector for Large Language Models Autodan: Generating stealthy jailbreak prompts on aligned large language models, 2024 b

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.767514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fb786464-b4e3-4e5a-9f41-8d8f5ac31202 · outbound

This paper cites FlipAttack: Jailbreak LLMs via Flipping.

Confidence Elicitation: A New Attack Vector for Large Language Models FlipAttack: Jailbreak LLMs via Flipping

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.915187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de135ef2-6a5a-4b40-939a-a6aca5ecf6ca · outbound

This paper cites At which training stage does code data help LLM s reasoning? In The Twelfth International Conference on Learning Representations, 2024.

Confidence Elicitation: A New Attack Vector for Large Language Models At which training stage does code data help LLM s reasoning? In The Twelfth International Conference on Learning Representations, 2024

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.756811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ba503021-ae33-4e33-938c-31770087a4ac · outbound

This paper cites Towards deep learning models resistant to adversarial attacks, 2019.

Confidence Elicitation: A New Attack Vector for Large Language Models Towards deep learning models resistant to adversarial attacks, 2019

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.922029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09dbc5ae-324f-42b1-b5ec-8c873be4c4a9 · outbound

This paper cites Generating Natural Language Attacks in a Hard Label Black Box Setting.

Confidence Elicitation: A New Attack Vector for Large Language Models Generating Natural Language Attacks in a Hard Label Black Box Setting

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.929089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2165e54e-bd21-48eb-a214-d6044b134154 · outbound

This paper cites Tree of attacks: Jailbreaking black-box LLM s automatically.

Confidence Elicitation: A New Attack Vector for Large Language Models Tree of attacks: Jailbreaking black-box LLM s automatically

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.739968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ccc52258-f62b-4fa7-84cd-293a857cff19 · outbound

This paper cites TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP.

Confidence Elicitation: A New Attack Vector for Large Language Models TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.935952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9da8935-d51f-4a9b-a792-c83e8760fea0 · outbound

This paper cites Counter-fitting word vectors to linguistic constraints, 2016.

Confidence Elicitation: A New Attack Vector for Large Language Models Counter-fitting word vectors to linguistic constraints, 2016

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.729303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 99814762-4a55-427c-bb9e-0018b059dc82 · outbound

This paper cites Strength in numbers: Estimating confidence of large language models by prompt agreement.

Confidence Elicitation: A New Attack Vector for Large Language Models Strength in numbers: Estimating confidence of large language models by prompt agreement

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.943199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b692972-5525-4574-90fd-5ffd3812d1a7 · outbound

This paper cites Extreme miscalibration and the illusion of adversarial robustness.

Confidence Elicitation: A New Attack Vector for Large Language Models Extreme miscalibration and the illusion of adversarial robustness

Reference 45

Resolution: verified exact; doi, observed 2026-08-08T22:06:39.165669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fb22cb1e-c1df-40a0-88fb-5a1eecd3561d · outbound

This paper cites Generating natural language adversarial examples through probability weighted word saliency.

Confidence Elicitation: A New Attack Vector for Large Language Models Generating natural language adversarial examples through probability weighted word saliency

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.949980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 433787ed-819e-4146-bb6d-81caca8aeef3 · outbound

This paper cites Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack.

Confidence Elicitation: A New Attack Vector for Large Language Models Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.953361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 698caa8c-9494-43b5-a1a5-1b55f3df3fe6 · outbound

This paper cites Second-order uncertainty quantification: A distance-based approach.

Confidence Elicitation: A New Attack Vector for Large Language Models Second-order uncertainty quantification: A distance-based approach

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.713315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1187fd41-1ccc-40ab-8e97-9cca394ffeb1 · outbound

This paper cites Large language model uncertainty measurement and calibration for medical diagnosis and treatment.

Confidence Elicitation: A New Attack Vector for Large Language Models Large language model uncertainty measurement and calibration for medical diagnosis and treatment

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.960140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af0b722a-1a5b-4b47-8dd2-e27701252ace · outbound

This paper cites Logan IV, Eric Wallace, and Sameer Singh.

Confidence Elicitation: A New Attack Vector for Large Language Models Logan IV, Eric Wallace, and Sameer Singh

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.963359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97c1b163-8670-4db1-842e-93bcfb764115 · outbound

This paper cites Intriguing properties of neural networks.

Confidence Elicitation: A New Attack Vector for Large Language Models Intriguing properties of neural networks

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.968013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84ec1773-6229-4829-8f1f-5bcab717b160 · outbound

This paper cites It’s morphin’ time! combating linguistic discrimination with inflectional perturbations.

Confidence Elicitation: A New Attack Vector for Large Language Models It’s morphin’ time! combating linguistic discrimination with inflectional perturbations

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.971928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a22275b-c838-4bd1-9d2e-7ee053dd98dc · outbound

This paper cites Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback.

Confidence Elicitation: A New Attack Vector for Large Language Models Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback

Reference 53

Resolution: malformed identifier; no resolver link, observed 2026-08-08T22:06:38.975593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72cc1b2a-8af4-49c4-bf2d-9aee28587879 · outbound

This paper cites Llama: Open and efficient foundation language models, 2023.

Confidence Elicitation: A New Attack Vector for Large Language Models Llama: Open and efficient foundation language models, 2023

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.979076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b15e501-be15-409a-bf6b-c9a51a6c8859 · outbound

This paper cites Calibrating large language models using their generations only, 2024.

Confidence Elicitation: A New Attack Vector for Large Language Models Calibrating large language models using their generations only, 2024

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.696891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8fdd3a8c-99ef-4bb1-af56-75cd58f315b1 · outbound

This paper cites CAT -gen: Improving robustness in NLP models via controlled adversarial text generation.

Confidence Elicitation: A New Attack Vector for Large Language Models CAT -gen: Improving robustness in NLP models via controlled adversarial text generation

Reference 56

Resolution: verified exact; doi, observed 2026-08-08T22:06:39.122881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b36c88fd-7cd2-49cd-8d5c-8157d288a653 · outbound

This paper cites Adversarial training with fast gradient projection method against synonym substitution based text attacks, 2020 b.

Confidence Elicitation: A New Attack Vector for Large Language Models Adversarial training with fast gradient projection method against synonym substitution based text attacks, 2020 b

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.686114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f6e96565-c004-4fc0-aa07-445f497f4a33 · outbound

This paper cites Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou.

Confidence Elicitation: A New Attack Vector for Large Language Models Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:38.993023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ab5336a-f3f1-4843-bcaa-f1f2059bf598 · outbound

This paper cites Stop reasoning! when multimodal LLM with chain-of-thought reasoning meets adversarial image.

Confidence Elicitation: A New Attack Vector for Large Language Models Stop reasoning! when multimodal LLM with chain-of-thought reasoning meets adversarial image

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.668721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6ebfcde3-9af6-40d6-8439-04f0f2a2fb40 · outbound

This paper cites Efficient Adversarial Training in LLMs with Continuous Attacks.

Confidence Elicitation: A New Attack Vector for Large Language Models Efficient Adversarial Training in LLMs with Continuous Attacks

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.000036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b033b79-1eba-46b0-823d-662a5c48207b · outbound

This paper cites Can LLM s express their uncertainty? an empirical evaluation of confidence elicitation in LLM s.

Confidence Elicitation: A New Attack Vector for Large Language Models Can LLM s express their uncertainty? an empirical evaluation of confidence elicitation in LLM s

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.003724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 094b0dbb-05e5-4da2-8b18-b13170dce54f · outbound

This paper cites An LLM can fool itself: A prompt-based adversarial attack.

Confidence Elicitation: A New Attack Vector for Large Language Models An LLM can fool itself: A prompt-based adversarial attack

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.652477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 75b5120f-16f1-4b63-9b73-d351c7b6e6cb · outbound

This paper cites Texthoaxer: Budgeted hard-label adversarial attacks on text.

Confidence Elicitation: A New Attack Vector for Large Language Models Texthoaxer: Budgeted hard-label adversarial attacks on text

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.010457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7396e07c-d9fa-4b27-9dfb-febd8771e42d · outbound

This paper cites Robust LLM safeguarding via refusal feature adversarial training.

Confidence Elicitation: A New Attack Vector for Large Language Models Robust LLM safeguarding via refusal feature adversarial training

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.013987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47a522f8-7b57-46dd-8f34-f847782b88ae · outbound

This paper cites T ext H acker: Learning based hybrid local search algorithm for text hard-label adversarial attack.

Confidence Elicitation: A New Attack Vector for Large Language Models T ext H acker: Learning based hybrid local search algorithm for text hard-label adversarial attack

Reference 65

Resolution: verified exact; doi, observed 2026-08-08T22:06:39.104300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a5cc5fbb-c26f-452c-9afd-9f88e7193be6 · outbound

This paper cites Word-level textual adversarial attacking as combinatorial optimization.

Confidence Elicitation: A New Attack Vector for Large Language Models Word-level textual adversarial attacking as combinatorial optimization

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.021017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ed9ab0e-3aec-4809-979b-34f74362d5ad · outbound

This paper cites Weak-to-Strong Jailbreaking on Large Language Models.

Confidence Elicitation: A New Attack Vector for Large Language Models Weak-to-Strong Jailbreaking on Large Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.024687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c052fa2-8a76-449a-970c-d50b95a4944b · outbound

This paper cites Freelb: Enhanced adversarial training for natural language understanding, 2020.

Confidence Elicitation: A New Attack Vector for Large Language Models Freelb: Enhanced adversarial training for natural language understanding, 2020

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.642273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5909f52b-7a61-4cee-a95b-1cf22e6a19ae · outbound

This paper cites Auto DAN : Automatic and interpretable adversarial attacks on large language models, 2024.

Confidence Elicitation: A New Attack Vector for Large Language Models Auto DAN : Automatic and interpretable adversarial attacks on large language models, 2024

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:07:24.632898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1bc43655-8808-4513-998e-d5b7dcfab70d · outbound

This paper cites Zico Kolter, and Matt Fredrikson.

Confidence Elicitation: A New Attack Vector for Large Language Models Zico Kolter, and Matt Fredrikson

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.035313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c472bca-1d33-47c5-8e4a-fc6c6a62b05c · outbound

This paper cites write newline.

Confidence Elicitation: A New Attack Vector for Large Language Models write newline

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.038666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9f9e5ad-4f3b-4f20-8dec-611662b5b6ca · outbound

This paper cites @esa (Ref.

Confidence Elicitation: A New Attack Vector for Large Language Models @esa (Ref

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.042566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99608ef3-78f9-46d0-aa74-a3e6914258a8 · outbound

This paper cites an unresolved cited work.

Confidence Elicitation: A New Attack Vector for Large Language Models Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.046484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58a96e54-cd1f-4ab0-b98f-c6899f1930fd · outbound

This paper cites jq5 ǝ.s] 5 o<tTK XXʵ 5? ouqͼς i 5צD.Vw \ b> ? E Bj< &_z r, Sփ p.

Confidence Elicitation: A New Attack Vector for Large Language Models jq5 ǝ.s] 5 o<tTK XXʵ 5? ouqͼς i 5צD.Vw \ b> ? E Bj< &_z r, Sփ p

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-08T22:06:39.050277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers