Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning | Paper Citation Record

Observation 268a9f57-319a-4c13-a9cc-6d97f22b82ec · outbound

This paper cites Scalable training of.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Scalable training of

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.203934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9503c7ab-737b-4b6c-b171-5b566f08c70b · outbound

This paper cites Tetreault , title =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Tetreault , title =

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.241765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e363e9-b134-4ada-a3d3-bf816c303c72 · outbound

This paper cites A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , volume =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , volume =

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.285496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04d16a38-0f21-415b-a5ff-0d1c0fc63bcc · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.349778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 808b8cd9-03dd-4762-8062-b412a1ecf0ff · outbound

This paper cites an unresolved cited work.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.497355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df50883e-b059-44e1-bf3d-00351034a58e · outbound

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

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.579244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f62de662-ba16-469b-892a-8b9e5e61e7c3 · outbound

This paper cites 2024 , url =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning 2024 , url =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.730128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7640626-c0c8-4179-bbfe-30df0102d0a3 · outbound

This paper cites Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images , booktitle =

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.785020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aad0b035-6efa-4719-b3c2-5aeb4463acb2 · outbound

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

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models , booktitle =

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.829239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 230005f1-b3d3-4889-9174-63d6b0b72c42 · outbound

This paper cites Jailbroken: How Does.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Jailbroken: How Does

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.884474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 523c6ef9-1a02-44fa-a8fb-3d5412493390 · outbound

This paper cites GPT-4 Technical Report.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning GPT-4 Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:22.953918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12a79ec7-62c7-426b-9e89-277f606d8751 · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:23.084880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9805f226-225d-4d76-9475-be8a53ab7e8e · outbound

This paper cites LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:23.346117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ede773-66ae-4237-8d0c-5b939c014180 · outbound

This paper cites First Conference on Language Modeling , year =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning First Conference on Language Modeling , year =

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:23.430629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d623042-1608-43f7-a927-cf9607c502ab · outbound

This paper cites Evil Geniuses: Delving into the Safety of LLM-based Agents.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Evil Geniuses: Delving into the Safety of LLM-based Agents

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:23.782759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70b746be-409b-48ea-b463-0b6b30333332 · outbound

This paper cites Attention Can Reflect Syntactic Structure (If You Let It) , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Attention Can Reflect Syntactic Structure (If You Let It) , booktitle =

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:23.986224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bf99afd-e3bd-40b5-a05c-3b19fdda406d · outbound

This paper cites Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:24.139384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb4a72e-a867-4d43-959f-000bd17be7e4 · outbound

This paper cites On Homophony and R.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning On Homophony and R

Reference 28

Resolution: verified exact; doi, observed 2026-08-06T04:47:26.017798Z

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 293e9d46-8622-4de1-9882-cf8ef8e6dd22 · outbound

This paper cites Shterionov and Matthew Gwilliam , editor =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Shterionov and Matthew Gwilliam , editor =

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:24.554229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9443664b-5e78-4fdb-b4ae-70d53d0e2e15 · outbound

This paper cites Entropy Rate Estimation for Markov Chains with Large State Space , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Entropy Rate Estimation for Markov Chains with Large State Space , booktitle =

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:24.707168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6894b06d-8ed5-402f-92e0-5a4d0f02999f · outbound

This paper cites Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing , booktitle =

Reference 31

Resolution: verified exact; doi, observed 2026-08-06T04:47:26.000793Z

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 cc5ecc72-7f73-4725-b4bb-b1c14e3c4b74 · outbound

This paper cites Shannon , title =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Shannon , title =

Reference 32

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-06T04:47:27.806722Z

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 23f494f7-cdc1-41f4-a666-705b5d9ae569 · outbound

This paper cites What does Attention in Neural Machine Translation Pay Attention to? , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning What does Attention in Neural Machine Translation Pay Attention to? , booktitle =

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.058042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e1890b-4151-44b2-9d2a-4c869dcdd797 · outbound

This paper cites Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists , booktitle =

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.063039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f8d3817-ab9e-4e22-9ec3-fb5884bad7b4 · outbound

This paper cites BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting , booktitle =

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.066419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9d27641-049e-411e-9429-58e7d31e42e5 · outbound

This paper cites Controlled Text Generation with Natural Language Instructions , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Controlled Text Generation with Natural Language Instructions , booktitle =

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.069482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1c78630-6f86-45e5-bf4d-504c42e10826 · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning SnapKV: LLM Knows What You are Looking for Before Generation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.072723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f659444-1eb3-4900-a5b9-b99afdb4d350 · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.076141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84dfebf8-d365-4540-b54e-1d89361e6052 · outbound

This paper cites Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization , booktitle =

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.079566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 240cc201-76cd-4c8e-a7c1-f9a8723ddd89 · outbound

This paper cites and Stoica, Ion and Xing, Eric P.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning and Stoica, Ion and Xing, Eric P

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.082655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac6945f3-f405-4197-b10a-4586ddd3ad87 · outbound

This paper cites Mistral 7B.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Mistral 7B

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.086087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17428ba0-a9c2-45de-8fcf-8226c1647016 · outbound

This paper cites LongBench:.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning LongBench:

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.089570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3296610d-420b-4c9a-a657-efc24edaea97 · outbound

This paper cites Hashimoto , editor =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Hashimoto , editor =

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.093166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a10ca096-16dd-4902-b7e7-971eb3b7478e · outbound

This paper cites ROUGE : A Package for Automatic Evaluation of Summaries.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning ROUGE : A Package for Automatic Evaluation of Summaries

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.096346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8d067be-6877-4e4f-af8b-c8240083be68 · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.099818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28913264-2a3c-462d-a4db-7165349957c0 · outbound

This paper cites AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.104226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c035543-a51e-4ded-9e62-4a46244f5525 · outbound

This paper cites RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.108472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdc42b29-3b87-43e9-a6cf-48eb35192df1 · outbound

This paper cites Forty-first International Conference on Machine Learning,.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Forty-first International Conference on Machine Learning,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.112045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca48cc06-146f-4c59-b53f-b0e421f5677c · outbound

This paper cites Cambridge (Mass.) , year=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Cambridge (Mass.) , year=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.115115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83dafb67-4289-4765-998c-66035bb5d752 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.119079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d6fc5db-10f9-453a-ae5f-0f1dfe37cfab · outbound

This paper cites The Twelfth International Conference on Learning Representations,.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning The Twelfth International Conference on Learning Representations,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.122830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eab2cfe-ff35-47ea-b193-636ce276f383 · outbound

This paper cites Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.126972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c19d35d-06fe-4cab-9ace-2fb85f4c9c6d · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.130779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86f5ac7a-f936-476b-af8e-d1f145e992fa · outbound

This paper cites Constituency Parsing with a Self-Attentive Encoder , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Constituency Parsing with a Self-Attentive Encoder , booktitle =

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.134843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60559ba7-5bad-4563-8330-db684460bab5 · outbound

This paper cites an unresolved cited work.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.138343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92d87fb3-dad1-4b95-b6b0-58f9c72ba017 · outbound

This paper cites Moses: Open Source Toolkit for Statistical Machine Translation , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Moses: Open Source Toolkit for Statistical Machine Translation , booktitle =

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.142775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b1cb66b-27b9-458f-ae20-a170e172979c · outbound

This paper cites The Second Tiny Papers Track at.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning The Second Tiny Papers Track at

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.146201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7988d8a-89bf-474b-93e7-a3c872f3f9d3 · outbound

This paper cites RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.150652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1cfcda2-590f-4fa8-b15e-01f4c01ba1f1 · outbound

This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers),.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers),

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.154435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 363f505c-5be9-44aa-8a1e-0946f08cd27b · outbound

This paper cites Linguistic Obfuscation Attacks and Large Language Model Uncertainty.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Linguistic Obfuscation Attacks and Large Language Model Uncertainty

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.160626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e8d6386-4b6b-475d-b8d4-75e4ed0bfcc3 · outbound

This paper cites Baseline defenses for adversarial attacks against aligned language models , url =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Baseline defenses for adversarial attacks against aligned language models , url =

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.163993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0572b867-c3ee-4b32-8ab2-8116a4cadc7d · outbound

This paper cites Jailbreak and guard aligned language models with only few in-context demonstrations , url =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Jailbreak and guard aligned language models with only few in-context demonstrations , url =

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.167197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f0920ac-b2e9-463e-9d48-bc9051477632 · outbound

This paper cites Entropy- and Distance-Regularized Attention Improves Low-Resource Neural Machine Translation , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Entropy- and Distance-Regularized Attention Improves Low-Resource Neural Machine Translation , booktitle =

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.177110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bae73e10-f23a-4f3f-aef0-d335a9fce043 · outbound

This paper cites SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-08-06T04:47:25.845928Z

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 b1a6e08a-2f62-499b-8543-ee1742fa93bf · outbound

This paper cites Pre-Trained Language Models for Text Generation:.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Pre-Trained Language Models for Text Generation:

Reference 68

Resolution: verified exact; doi, observed 2026-08-06T04:47:25.831874Z

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 18d1b30f-ec20-4e5c-a5f0-820895b24f35 · outbound

This paper cites Zhao and Kelvin Guu and Adams Wei Yu and Brian Lester and Nan Du and Andrew M.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Zhao and Kelvin Guu and Adams Wei Yu and Brian Lester and Nan Du and Andrew M

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.193774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72c6cf0d-de0c-4fb9-b7f6-4a893b36f71f · outbound

This paper cites MetaICL: Learning to Learn In Context , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning MetaICL: Learning to Learn In Context , booktitle =

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.197914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70196302-b992-4392-b08a-69143110e473 · outbound

This paper cites Intention Analysis Makes LLMs.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Intention Analysis Makes LLMs

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.206467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0e2f18f-529d-4dbd-8425-92f414b339cb · outbound

This paper cites How Alignment and Jailbreak Work: Explain.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning How Alignment and Jailbreak Work: Explain

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.210421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24007d6f-f2b0-4a59-95c4-aa172ff58fa1 · outbound

This paper cites PeerJ Comput.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning PeerJ Comput

Reference 74

Resolution: verified exact; doi, observed 2026-08-06T04:47:25.800552Z

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 a073eb1d-e7ef-4156-b249-9a3328404f01 · outbound

This paper cites Attack Prompt Generation for Red Teaming and Defending Large Language Models , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Attack Prompt Generation for Red Teaming and Defending Large Language Models , booktitle =

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.219735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd14e349-c28d-47d8-ac2a-85c2f779f405 · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.223831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13dfcf86-c9ab-4585-b6a7-6355e365c53c · outbound

This paper cites Baratz , title =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Baratz , title =

Reference 78

Resolution: verified exact; doi, observed 2026-08-06T04:47:25.765691Z

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 c06a68ee-93e3-43dd-b662-e67acb8e06f7 · outbound

This paper cites Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction , booktitle =

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.237270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3518894c-b202-4e05-80c3-ebdb77e58f73 · outbound

This paper cites Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.242656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4bce729-d152-48ad-b39a-39c4175bae79 · outbound

This paper cites The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models , booktitle =

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.251376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0e2e961-8ecc-4650-a146-5e4b5d52edce · outbound

This paper cites Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction

Reference 84

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T04:47:27.349009Z

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 0d110ef1-6a15-433f-8729-ac3f195ad55f · outbound

This paper cites Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks , pages =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks , pages =

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.268512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cedf998-d355-4f9c-a7cb-8d82a42e6a9a · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2024 , pages=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.272535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d62732f-eedf-4992-90d0-6df84b72ea84 · outbound

This paper cites Measuring short-form factuality in large language models.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Measuring short-form factuality in large language models

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.277099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8006431-c724-4277-9aac-e50ae2e0d3d4 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning The Twelfth International Conference on Learning Representations , year=

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.281090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abaabf95-e299-4594-b64c-261201fd8cad · outbound

This paper cites Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks , year=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks , year=

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.285074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0729250e-f276-435f-94b9-7343aa15fff9 · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning The Thirteenth International Conference on Learning Representations , year=

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.317349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1494bbd0-6248-45e8-9970-2732273e9611 · outbound

This paper cites Communication theory , volume=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Communication theory , volume=

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.326091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d00cb1df-6a9b-4bbb-883c-4f1a741dbaa1 · outbound

This paper cites 1995 , publisher=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning 1995 , publisher=

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.330260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca816e23-6557-406c-91c9-fd3e57df965b · outbound

This paper cites Trends in cognitive sciences , volume=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Trends in cognitive sciences , volume=

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.334970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f18300b-f2d1-41b9-8785-7ff8f5fc1af1 · outbound

This paper cites 2024 , month=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning 2024 , month=

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.369365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36d37510-f511-4990-88c5-a821196c5fb8 · outbound

This paper cites QwQ: Reflect Deeply on the Boundaries of the Unknown , url =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning QwQ: Reflect Deeply on the Boundaries of the Unknown , url =

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.379069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd813bac-0f99-4381-ae25-604a9b32a669 · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Advances in Neural Information Processing Systems , volume =

Reference 115

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.402012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4297303-9b4b-43b4-9aa7-5460a3134d68 · outbound

This paper cites , title =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning , title =

Reference 116

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.405231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78656b56-a65e-4937-9b0f-81deb8033ec0 · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 117

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.409130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b161fc8-cad1-47bc-b8b5-2168d35bbe55 · outbound

This paper cites , title =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning , title =

Reference 118

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.412954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d9ed9de-567a-417b-b4bb-ef3ee8b1b83d · outbound

This paper cites SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages

Reference 119

Resolution: verified exact; local_arxiv, observed 2026-08-06T04:47:26.647570Z

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 01dd707c-d916-4be1-a539-cb156461a218 · outbound

This paper cites Recursively Summarizing Books with Human Feedback.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Recursively Summarizing Books with Human Feedback

Reference 120

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.420772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1d601b9-a726-4d89-b7a5-2715dc087c9e · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 121

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.424543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6735acff-92f5-4e47-a1e8-a09b988f2502 · outbound

This paper cites RRHF: Rank Responses to Align Language Models with Human Feedback without tears.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning RRHF: Rank Responses to Align Language Models with Human Feedback without tears

Reference 122

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.428063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41920adb-1683-4200-8229-c1a719ed27e6 · outbound

This paper cites Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game

Reference 123

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.431886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ded2693-e7ac-44c7-9a55-76436bba48b2 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 124

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.435933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 124b0350-2760-4f7e-b20e-1f16c3564d47 · outbound

This paper cites WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs , booktitle =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs , booktitle =

Reference 125

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.439206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f3ecc9-3037-4b72-84c4-e07cacb3ab50 · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Advances in Neural Information Processing Systems , volume =

Reference 126

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.443067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6526227b-df7c-4f12-975b-78054af02f30 · outbound

This paper cites Advances in Neural Information Processing Systems , editor=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Advances in Neural Information Processing Systems , editor=

Reference 127

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.446317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b359990e-2384-4ad7-b1e0-a39c77335c92 · outbound

This paper cites Nature Machine Intelligence , volume=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Nature Machine Intelligence , volume=

Reference 128

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.449331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce84f680-4574-4c16-b59b-b57af2283133 · outbound

This paper cites R ^2 -Guard: Robust Reasoning Enabled.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning R ^2 -Guard: Robust Reasoning Enabled

Reference 129

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.452672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0fc8aea-2e5b-4e63-82a5-02d81fae1a96 · outbound

This paper cites Intention Analysis Makes LLM s A Good Jailbreak Defender.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Intention Analysis Makes LLM s A Good Jailbreak Defender

Reference 131

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.459774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0afa17f4-6218-49be-8bf7-e5e7f6175f3c · outbound

This paper cites ICLR 2025 Workshop on Bidirectional Human-AI Alignment , year=.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning ICLR 2025 Workshop on Bidirectional Human-AI Alignment , year=

Reference 132

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.463034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28e710ac-1742-4498-810c-7a01214204bc · outbound

This paper cites The Twelfth International Conference on Learning Representations,.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning The Twelfth International Conference on Learning Representations,

Reference 135

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.472656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89fb7cc2-b44f-441e-b961-3d9725989ba0 · outbound

This paper cites The Thirteenth International Conference on Learning Representations,.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning The Thirteenth International Conference on Learning Representations,

Reference 137

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.478908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baa92770-d2e3-4211-af5f-411131d9fb81 · outbound

This paper cites an unresolved cited work.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Unresolved cited work

Reference 139

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.485427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7785b622-6dda-4b27-aad4-23b43b6ed235 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Detecting Language Model Attacks with Perplexity

Reference 141

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.491763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a759f6b1-57ed-476d-a788-a50e8111befd · outbound

This paper cites an unresolved cited work.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Unresolved cited work

Reference 142

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.494752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers