Large Language Model Adversarial Landscape Through the Lens of Attack Objectives | Paper Citation Record

Observation 779a59b4-5326-4312-a74a-dfff88d743dc · outbound

This paper cites Quantifying privacy risks of masked language models using membership inference attacks,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Quantifying privacy risks of masked language models using membership inference attacks,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.878963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41c3239e-1410-4ea5-999e-b275f1534e11 · outbound

This paper cites An empirical analysis of memorization in fine-tuned autoregressive language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives An empirical analysis of memorization in fine-tuned autoregressive language models,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.885274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcdf25c0-2c7a-41ff-93e9-29138a8dfd55 · outbound

This paper cites Membership Inference Attacks against Language Models via Neighbourhood Comparison.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Membership Inference Attacks against Language Models via Neighbourhood Comparison

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.890895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9deaa668-e970-4dd3-b7da-9a0082b88612 · outbound

This paper cites Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.897327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c40a2f-82de-4342-ae64-a7ef4823dfda · outbound

This paper cites Gradient-based Adversarial Attacks against Text Transformers.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Gradient-based Adversarial Attacks against Text Transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.903229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbb59246-0ea7-46db-b807-bf6652108343 · outbound

This paper cites Black Box Adversarial Prompting for Foundation Models.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Black Box Adversarial Prompting for Foundation Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.909350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db709750-b4c6-428b-b5ae-aa3f11dbd7d3 · outbound

This paper cites Sponge examples: Energy-latency attacks on neural networks,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Sponge examples: Energy-latency attacks on neural networks,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.915885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe2f31d1-204c-45db-87c1-7d02a2b0d420 · outbound

This paper cites The skipsponge attack: Sponge weight poisoning of deep neural networks,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives The skipsponge attack: Sponge weight poisoning of deep neural networks,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.921380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a777596-80af-48c8-b0b4-4dfd32229065 · outbound

This paper cites BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.926458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 995d862d-9357-4648-b6aa-9b2beed85019 · outbound

This paper cites Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.931875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92087abb-dcb0-4cf1-aaf2-c880a8bcdce5 · outbound

This paper cites Jailbroken: How does llm safety training fail?.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Jailbroken: How does llm safety training fail?

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.937164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bca425bf-1acb-4d80-841d-c3fd08864da5 · outbound

This paper cites Masterkey: Automated jailbreaking of large language model chatbots,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Masterkey: Automated jailbreaking of large language model chatbots,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.942178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aebabad7-a43b-4edd-9f45-f7b5f7d9ac9c · outbound

This paper cites Low-resource lan- guages jailbreak gpt-4,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Low-resource lan- guages jailbreak gpt-4,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.947217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b9bcac8-9ae9-4525-9a19-bd95db159a94 · outbound

This paper cites RRHF: rank responses to align language models with human feedback,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives RRHF: rank responses to align language models with human feedback,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.952312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd0a7d43-5122-4bbc-b63a-2a756102bda9 · outbound

This paper cites Security and Privacy Challenges of Large Language Models: A Survey.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Security and Privacy Challenges of Large Language Models: A Survey

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.957573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0378fa5-1859-43d7-895a-17e2b22223bb · outbound

This paper cites Unique security and privacy threats of large language model: A comprehensive survey,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Unique security and privacy threats of large language model: A comprehensive survey,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.962958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ad21f5-47e0-411d-a5f6-8f19eb505419 · outbound

This paper cites Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.967993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65153636-eaff-4879-b51d-f68063d5b45d · outbound

This paper cites Breaking down the defenses: A comparative survey of attacks on large language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Breaking down the defenses: A comparative survey of attacks on large language models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.973357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8d434f7-f535-4237-b046-cd1225ee0d1a · outbound

This paper cites A survey on large language model (llm) security and privacy: The good, the bad, and the ugly,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives A survey on large language model (llm) security and privacy: The good, the bad, and the ugly,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.978509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cb37f0c-3d15-4aca-9a81-eb28e3e36c64 · outbound

This paper cites Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.983629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8a8fa1d-2984-4f45-bdd1-d2a2ad54f320 · outbound

This paper cites Privacy Side Channels in Machine Learning Systems.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Privacy Side Channels in Machine Learning Systems

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-09T10:29:51.313274Z

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 3f72908d-90ab-427c-8799-5dc8b064bdf1 · outbound

This paper cites Extracting training data from large language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Extracting training data from large language models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.994381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7a9df9f-6b17-49af-a957-e5366528a70c · outbound

This paper cites Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.004481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89257ba0-bdc9-4ab2-9738-27bcfce1e6bf · outbound

This paper cites Deep Leakage from Gradients.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Deep Leakage from Gradients

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.009850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d54ee97-8d13-4b2e-86df-9874747309ee · outbound

This paper cites A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.014690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3efd2ac7-ff19-44dc-b02a-9eb1a30ea79b · outbound

This paper cites Model leeching: An extraction attack targeting llms,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Model leeching: An extraction attack targeting llms,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.020105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96360e29-b26d-409c-9855-b0c13b2a0746 · outbound

This paper cites Prompt injection attack against llm-integrated applications,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Prompt injection attack against llm-integrated applications,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.025185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3e80c8-957a-4412-8773-ea7dc1347c39 · outbound

This paper cites Effective Prompt Extraction from Language Models.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Effective Prompt Extraction from Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.030145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5842d16d-8d1f-44c5-8227-e936ab9139c8 · outbound

This paper cites The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-09T10:29:51.199889Z

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 ed4d8bc0-5d0e-453a-a005-c4ff380858a5 · outbound

This paper cites Multi-step jailbreaking privacy attacks on chatgpt,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Multi-step jailbreaking privacy attacks on chatgpt,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.040248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfd102d3-7ad6-470d-83af-2846c683e55c · outbound

This paper cites Badpre: Task-agnostic backdoor attacks to pre-trained NLP foun- dation models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Badpre: Task-agnostic backdoor attacks to pre-trained NLP foun- dation models,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.584283Z

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 6c1c5dfa-d7aa-4dae-98b4-bd5b4200e3d0 · outbound

This paper cites Composite backdoor attacks against large language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Composite backdoor attacks against large language models,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.568430Z

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 bd0f4184-31b1-470a-ba8c-b7416d6c0bde · outbound

This paper cites Backdoor attacks for in-context learning with language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Backdoor attacks for in-context learning with language models,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.553102Z

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 b5afd884-a4f8-484e-8681-bada0c27234f · outbound

This paper cites Badedit: Backdooring large language models by model editing,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Badedit: Backdooring large language models by model editing,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.536460Z

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 104c0c6c-0a95-439d-98bc-f0ac8b3441a0 · outbound

This paper cites Weight poisoning attacks on pretrained models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Weight poisoning attacks on pretrained models,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.517375Z

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 5c2fce5d-2772-4ab2-a49d-841329a74b9c · outbound

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

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Backdoor attacks on pre-trained models by layerwise weight poisoning,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.498615Z

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 e8c064ac-2385-4a54-81c3-531e019f7bbb · outbound

This paper cites Catastrophic interference in con- nectionist networks: The sequential learning problem,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Catastrophic interference in con- nectionist networks: The sequential learning problem,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.482663Z

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 4834bdd4-b249-44f7-acb6-b65eeecd8104 · outbound

This paper cites Red alarm for pre-trained models: Universal vul- nerability to neuron-level backdoor attacks,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Red alarm for pre-trained models: Universal vul- nerability to neuron-level backdoor attacks,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.465334Z

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 0ec9a2fd-054a-4cba-b80c-12034ffe5170 · outbound

This paper cites Uor: Universal backdoor attacks on pre-trained language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Uor: Universal backdoor attacks on pre-trained language models,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.450065Z

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 742eb058-6c6b-4ead-8bed-ff69863269af · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Discovering Language Model Behaviors with Model-Written Evaluations

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.094426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c8e2cb1-216d-46e0-b20f-70989f7e1828 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Explaining and Harnessing Adversarial Examples

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.099679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83acc41c-f98b-4843-891c-bac937b09a2f · outbound

This paper cites Universal and transferable adversarial attacks on aligned language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Universal and transferable adversarial attacks on aligned language models,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.104633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c852828-557e-440a-a24d-2c3ad121004b · outbound

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

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Autodan: Generating stealthy jailbreak prompts on aligned large language models,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.423973Z

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 077b5a60-4f00-4ccc-9698-ff06e00b93fe · outbound

This paper cites Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.408502Z

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 40d59864-3713-4dba-b09d-52fe250163c7 · outbound

This paper cites CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.118656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27f0611d-9193-431a-8cb0-989a89a3d341 · outbound

This paper cites Multilingual jailbreak challenges in large language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Multilingual jailbreak challenges in large language models,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.393195Z

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 5227bde8-5717-452b-9f8e-c3dc72e65ea3 · outbound

This paper cites Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.377291Z

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 0515fb4d-df96-4296-b060-edbed182c801 · outbound

This paper cites ”do anything now.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives ”do anything now

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.362042Z

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 b4fffba4-2b19-4bdb-8a92-bd91badb5898 · outbound

This paper cites Ignore previous prompt: Attack techniques for language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Ignore previous prompt: Attack techniques for language models,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.345773Z

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 f0427670-fd64-4894-9a69-e43880894ff9 · outbound

This paper cites Why so toxic?: Measuring and triggering toxic behavior in open-domain chatbots,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Why so toxic?: Measuring and triggering toxic behavior in open-domain chatbots,

Reference 50

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T10:29:51.075789Z

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 2b4f8853-b7c4-49ce-8e56-4e03c9cb7764 · outbound

This paper cites Explore, establish, exploit: Red teaming language models from scratch,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Explore, establish, exploit: Red teaming language models from scratch,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.330471Z

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 cdcff83d-d586-4c55-8efe-e00b41756c80 · outbound

This paper cites Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.314575Z

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 13f5a61b-32ba-4cca-b300-9c58af05f6c7 · outbound

This paper cites Fuzzllm: A novel and universal fuzzing framework for proactively discovering jailbreak vulnerabilities in large language models,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Fuzzllm: A novel and universal fuzzing framework for proactively discovering jailbreak vulnerabilities in large language models,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.297264Z

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 0b0002ce-0557-4128-a8ae-f6ee1b87327d · outbound

This paper cites Parafuzz: An interpretability-driven technique for de- tecting poisoned samples in NLP,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Parafuzz: An interpretability-driven technique for de- tecting poisoned samples in NLP,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.281573Z

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 35a58323-36bb-4a64-adf3-4a2dbedf27de · outbound

This paper cites Jailbreaking black box large language models in twenty queries,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Jailbreaking black box large language models in twenty queries,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.266148Z

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 b4306fb1-7467-443d-95f9-1f0994c11411 · outbound

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

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.179302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bf59265-0dd6-4541-b5de-34e079a08d67 · outbound

This paper cites Automatically auditing large language models via discrete optimization,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Automatically auditing large language models via discrete optimization,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.250283Z

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 048c2f03-0df1-4d44-a70b-8d025ac9751c · outbound

This paper cites Eraser: Jailbreaking defense in large language models via unlearning harmful knowledge,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Eraser: Jailbreaking defense in large language models via unlearning harmful knowledge,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.234306Z

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 be87d481-dcf7-4fbc-b8cd-485ef85dbc5d · outbound

This paper cites Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.195132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c5e495d-5ff0-4b45-b5e8-e1887e7cc09e · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.200326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7784d2aa-4407-48d7-842c-5ef5d2381eb3 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.205234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d530286-2a76-4e7c-8c91-8634aaf7e179 · outbound

This paper cites Break the breakout: Reinventing lm defense against jailbreak attacks with self-refinement,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Break the breakout: Reinventing lm defense against jailbreak attacks with self-refinement,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.215217Z

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 0a71edbd-db34-46a8-ac1a-3efcf17f271d · outbound

This paper cites Safe rlhf: Safe reinforcement learning from human feedback,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Safe rlhf: Safe reinforcement learning from human feedback,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.197830Z

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 2d8449b8-7072-4e9f-99b6-95d61814dce7 · outbound

This paper cites Smoothllm: Defending large language models against jailbreaking attacks,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Smoothllm: Defending large language models against jailbreaking attacks,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.183392Z

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 f978740d-617e-446f-9e2b-15e15f6ce5de · outbound

This paper cites Defending large language models against jailbreak attacks via semantic smoothing,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Defending large language models against jailbreak attacks via semantic smoothing,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.168514Z

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 6fdf60ee-d52b-4f45-8aa0-2797d7f35a9f · outbound

This paper cites Certified adversarial robustness via randomized smoothing,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Certified adversarial robustness via randomized smoothing,

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.153285Z

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 f4ae7ac6-010a-48fd-a012-e9042fa0a704 · outbound

This paper cites Dp-forward: Fine-tuning and inference on language models with differential privacy in forward pass,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Dp-forward: Fine-tuning and inference on language models with differential privacy in forward pass,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.138024Z

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 64256897-cf8a-4449-8d82-8bfdd6f80501 · outbound

This paper cites Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.240137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60bbd7e6-be9f-4635-b192-375e4f27b423 · outbound

This paper cites Defending large language models against jailbreaking attacks through goal prioritization,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Defending large language models against jailbreaking attacks through goal prioritization,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.121510Z

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 5f23e21c-01d7-468d-8e17-a000b7b8c9da · outbound

This paper cites RAIN: Your language models can align themselves without finetuning,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives RAIN: Your language models can align themselves without finetuning,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.105189Z

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 4cc1a48c-479a-4f1d-9e7b-0b554279d249 · outbound

This paper cites RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.255222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97eccaa6-3b7e-4e6b-be93-404d0c29c8de · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Direct preference optimization: Your language model is secretly a reward model,

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.087339Z

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 7b237172-e5fa-40f2-b031-b023707127b0 · outbound

This paper cites From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.265334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be44f680-60a2-493c-ad89-f9d3708c9b3b · outbound

This paper cites Design and evaluation of a multi- domain trojan detection method on deep neural networks,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Design and evaluation of a multi- domain trojan detection method on deep neural networks,

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.069775Z

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 1141e4e6-3988-403d-864d-f742034deac8 · outbound

This paper cites Robust backdoor detection for deep learning via topological evolution dynamics,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Robust backdoor detection for deep learning via topological evolution dynamics,

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.053920Z

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 0cbbc101-2f9d-4492-8e00-572d169b4c84 · outbound

This paper cites Mm-bd: Post- training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum margin statistic,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Mm-bd: Post- training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum margin statistic,

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.038290Z

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 853ca252-4148-4341-8233-2c489103a4b6 · outbound

This paper cites Locating and editing factual associations in gpt,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Locating and editing factual associations in gpt,

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.020986Z

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 b91e0cd2-87c9-4734-8b1c-d89933be58a3 · outbound

This paper cites A Comprehensive Study of Knowledge Editing for Large Language Models.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives A Comprehensive Study of Knowledge Editing for Large Language Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.293237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d634e7a-1b0e-473a-bcc2-664e7f81050d · outbound

This paper cites Federatedscope- llm: A comprehensive package for fine-tuning large language models in federated learning,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Federatedscope- llm: A comprehensive package for fine-tuning large language models in federated learning,

Reference 79

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T10:29:50.743851Z

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 796a0fff-ec26-4fc1-8526-7dd636e02b40 · outbound

This paper cites How to backdoor federated learning,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives How to backdoor federated learning,

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:52.004673Z

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 769c9347-0e6a-4b61-96b6-9b0abe01142d · outbound

This paper cites Attack of the tails: Yes, you really can backdoor federated learning,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Attack of the tails: Yes, you really can backdoor federated learning,

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.989077Z

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 182aaf0f-e1e7-4150-bc29-8eb9bedd3727 · outbound

This paper cites DBA: distributed backdoor attacks against federated learning,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives DBA: distributed backdoor attacks against federated learning,

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.974097Z

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 38c9bc5d-b4b3-4c9a-928f-617c61e5c2cc · outbound

This paper cites Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.955797Z

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 6da44e5d-9e0f-41bb-ab92-b4704528b939 · outbound

This paper cites Practical secure aggregation for privacy-preserving machine learning,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Practical secure aggregation for privacy-preserving machine learning,

Reference 84

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T10:29:50.579361Z

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 b0b1a240-6da9-4ce0-8285-502205b7c9c7 · outbound

This paper cites Machine learning with adversaries: Byzantine tolerant gradient descent,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Machine learning with adversaries: Byzantine tolerant gradient descent,

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.940389Z

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 d392ee61-5182-4c61-8bc0-ef952115368e · outbound

This paper cites The hidden vulnerability of distributed learning in byzantium,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives The hidden vulnerability of distributed learning in byzantium,

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.924697Z

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 942fd518-9702-4825-bb2a-6d3830160b91 · outbound

This paper cites Fltrust: Byzantine- robust federated learning via trust bootstrapping,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Fltrust: Byzantine- robust federated learning via trust bootstrapping,

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.907660Z

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 a161a009-1845-4592-be2b-ecf827a117f0 · outbound

This paper cites FLAME: taming backdoors in federated learning,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives FLAME: taming backdoors in federated learning,

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.890051Z

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 cfb7fb49-4fa8-4abe-851c-a0d374bfc126 · outbound

This paper cites Calibrating noise to sensitivity in private data analysis,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Calibrating noise to sensitivity in private data analysis,

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.874529Z

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 1a200729-1063-409b-b03e-d3d55856d2fa · outbound

This paper cites CRFL: certifiably robust federated learning against backdoor attacks,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives CRFL: certifiably robust federated learning against backdoor attacks,

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.840239Z

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 15684c4c-5afb-40d4-9c36-1600e1843c5d · outbound

This paper cites Yes, one-bit-flip matters! universal dnn model infer- ence depletion with runtime code fault injection,.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Yes, one-bit-flip matters! universal dnn model infer- ence depletion with runtime code fault injection,

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:29:51.815803Z

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 9c9bf0fe-1e48-4a6d-87d3-56f181b44334 · outbound

This paper cites Multi-step Jailbreaking Privacy Attacks on ChatGPT.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Multi-step Jailbreaking Privacy Attacks on ChatGPT

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.045250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed493799-d566-405d-aa80-3f587e1ba4f4 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:50.133416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7386865-4023-43c7-87bc-dabb6c8be476 · outbound

This paper cites Available: https://www.usenix.org/conference/ usenixsecurity21/presentation/carlini-extracting.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Available: https://www.usenix.org/conference/ usenixsecurity21/presentation/carlini-extracting

Reference 2650

Resolution: unresolved; no resolver link, observed 2026-08-09T10:29:49.999202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aba607c0-3780-4ffc-9f3b-86167f74b640 · outbound

This paper cites an unresolved cited work.

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives Unresolved cited work

Reference 3876

Resolution: unresolved; raw_fallback, observed 2026-08-09T10:29:51.858717Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers