Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T05:36:58.179549Z
Paper Citation Record · LEDGER
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts
As of 11 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 2 inbound Pith citation observations for arXiv:2506.07596.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-03T01:03:28.012736Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Reference resolution
75 of 75 outbound references displayed
- verified exact0
- verified fuzzy42
- unresolved30
- parse uncertain1
- malformed identifier2
- metadata mismatch0
External citation measurements
0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation c4667882-bb7d-4cfd-85df-ff0099d9668e · outbound
This paper cites DeepSeek LLM 7B Chat.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts DeepSeek LLM 7B Chat
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.375949Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 3d7b51bc-6d31-47f2-8e95-ad80061bfea1 · outbound
This paper cites Mistral 7B Instruct v0.2.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Mistral 7B Instruct v0.2
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.363168Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c069bfaa-ee30-474d-a255-197e21c74855 · outbound
This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:57.822710Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1acdfa2e-b844-4d38-9089-dd432d6eead2 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 4
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:59.349778Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f2d19aa2-596e-4e64-b8d3-bfcfd339d83e · outbound
This paper cites Language Models are Few-Shot Learn- ers.NeurIPS, 2020.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Language Models are Few-Shot Learn- ers.NeurIPS, 2020
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.336081Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a331f1c4-8f63-4135-9629-dcc32f00318b · outbound
This paper cites A review of the application of deep learning in medical image classifica- tion and segmentation.Annals of translational medicine, 2020.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts A review of the application of deep learning in medical image classifica- tion and segmentation.Annals of translational medicine, 2020
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.322660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0655e8a1-bcb6-4e6a-8913-731f5ce195af · outbound
This paper cites Pappas, and Eric Wong.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Pappas, and Eric Wong
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.307761Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 6b8b0bce-50ce-4393-be4c-9ae5f8df441e · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 8
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:59.294077Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f3967756-c0a0-4bf6-bb83-c4028c29d2c7 · outbound
This paper cites DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving.ICCV, 2015.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving.ICCV, 2015
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.281067Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation ae499608-f5c4-4355-9d51-595d9c438154 · outbound
This paper cites Finding Safety Neurons in Large Language Models.arXiv preprint arXiv:2406.14144, 2024.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Finding Safety Neurons in Large Language Models.arXiv preprint arXiv:2406.14144, 2024
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:57.860304Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fad7322a-2904-413d-a846-f0a374e9ed92 · outbound
This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:57.865187Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 932cb4ec-7843-46b8-b39b-05682e2d5e9e · outbound
This paper cites Natural language processing (almost) from scratch.JMLR, 2011.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Natural language processing (almost) from scratch.JMLR, 2011
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.267292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation cc1c97ba-0ad4-4583-ab56-b3d1a3c3fae6 · outbound
This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:57.876865Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f7328520-9651-4cc2-8ba3-00c44b3ec280 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:59.254081Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 57aaf956-792b-4db4-9ad4-2785be8e1762 · outbound
This paper cites BERT: Pre-training of Deep Bidi- rectional Transformers for Language Understanding.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts BERT: Pre-training of Deep Bidi- rectional Transformers for Language Understanding
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.240256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 42cb55e0-6667-4d2d-8093-0bfbe573e7a7 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:59.226412Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c4863368-b26d-416d-baef-3730e1746f6a · outbound
This paper cites Gemma 2 27B Instruction Tuned.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gemma 2 27B Instruction Tuned
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.213377Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 30fc7dca-2646-47ee-8ab8-a4d3c2da007a · outbound
This paper cites Gemma 2 2B Instruction Tuned.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gemma 2 2B Instruction Tuned
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.199591Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 200dba93-d003-4897-8520-44ece877a7c7 · outbound
This paper cites Gemma 2 9B Instruction Tuned.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gemma 2 9B Instruction Tuned
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.185368Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 1464180f-c9d3-4464-b93f-f2275742024a · outbound
This paper cites Gemma 3 1B Instruction Tuned.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gemma 3 1B Instruction Tuned
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.171365Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation bdd14b95-6036-4ae1-a189-075d134d296d · outbound
This paper cites Gemma: Open Models Based on Gemini Research and Technology.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gemma: Open Models Based on Gemini Research and Technology
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:57.915684Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 431344a7-d44f-4f3a-bf82-d595cbc63baf · outbound
This paper cites Qwen 2.5 14B Instruct.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Qwen 2.5 14B Instruct
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.157128Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation b7c66642-f910-40c4-91bd-ab7449e7134e · outbound
This paper cites Qwen 2.5 32B Instruct.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Qwen 2.5 32B Instruct
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.142520Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 4c59e1ed-02f6-457d-aa21-46947755431a · outbound
This paper cites Qwen 2.5 3B Instruct.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Qwen 2.5 3B Instruct
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.127811Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 9c172ed8-f26e-49c7-a4e6-da1b4df6fe5e · outbound
This paper cites Qwen 2.5 72B Instruct.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Qwen 2.5 72B Instruct
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.110308Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 1d7656d8-32cf-4e92-9408-ccdd39a76e4f · outbound
This paper cites Qwen 2.5 7B Instruct.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Qwen 2.5 7B Instruct
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.095820Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation bbb9fb27-09b9-430d-a1b3-7d721c7a8dca · outbound
This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:57.943727Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a738dcef-d76c-4ae6-be27-07bea86ff41c · outbound
This paper cites Gradient-based Adversarial Attacks against Text Transformers.EMNLP, 2021.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gradient-based Adversarial Attacks against Text Transformers.EMNLP, 2021
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.082522Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 64e0cd0e-73e9-4e3e-8b36-c9d254f5faad · outbound
This paper cites Hugging Face.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Hugging Face
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.069582Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 748dbe20-cb50-49e2-a38a-ab0b7eac7bc3 · outbound
This paper cites Mistral 7B.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Mistral 7B
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:57.959074Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a98b255-044c-4f91-9418-8c11c29573d3 · outbound
This paper cites Kaggle: Your Home for Data Science.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Kaggle: Your Home for Data Science
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.056619Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 43d0d9ca-796d-4538-9d5a-e15e259e16e5 · outbound
This paper cites Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks.IEEE SPW, 2024.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks.IEEE SPW, 2024
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.043152Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 235d7e53-e848-4e48-a9ea-61b50c1785c7 · outbound
This paper cites TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts.USENIX Security, 2025.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts.USENIX Security, 2025
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.029104Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation af9b9e39-8dc0-4736-8177-cb71e19cf6d6 · outbound
This paper cites SentencePiece: A simple and language-independent subword tokenizer and detokenizer for Neural Text Processing.EMNLP, 2018.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts SentencePiece: A simple and language-independent subword tokenizer and detokenizer for Neural Text Processing.EMNLP, 2018
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:59.016149Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 3ca1d9e0-2426-4105-a641-d716a1143aef · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 35
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:59.002599Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a4bf452f-dc18-4ae3-a9c0-0c89bd18d61a · outbound
This paper cites Backdoor Learning: A Survey.IEEE Transactions on Neural Networks and Learning Systems, 2022.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Backdoor Learning: A Survey.IEEE Transactions on Neural Networks and Learning Systems, 2022
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.989392Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 46d91521-766a-42a7-8fc2-d4c8953ad6a5 · outbound
This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.ICLR, 2024.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.ICLR, 2024
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.975576Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation b44450f2-c569-40fa-9b84-495b8ccdc68b · outbound
This paper cites Prompt Injection attack against LLM-integrated Applications.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Prompt Injection attack against LLM-integrated Applications
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:57.997650Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 419a786a-5820-4356-8525-bf33c695aa41 · outbound
This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.003299Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c522ee51-582c-4774-8227-eea8ba257110 · outbound
This paper cites Llama 2 13B Chat.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Llama 2 13B Chat
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.960942Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 1b48a51d-a368-4e5b-9b0c-4e9c641c6535 · outbound
This paper cites Llama 2 70B Chat.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Llama 2 70B Chat
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.947422Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 5c1a7478-a653-487b-9896-6be0a84ccd9c · outbound
This paper cites Llama 2 7B Chat.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Llama 2 7B Chat
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.933489Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 81429a98-3c39-4cd1-bb79-804aabad1ffc · outbound
This paper cites Llama 3.1 8B Instruct.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Llama 3.1 8B Instruct
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.919872Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 50edf83d-8106-4130-9231-a9a0265b565a · outbound
This paper cites Llama 3.3 70B Instruct.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Llama 3.3 70B Instruct
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.905409Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 1d7dd1f0-a501-46db-a3bf-621a22213e6a · outbound
This paper cites Llama guard 3 8b.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Llama guard 3 8b
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.891368Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 87a12934-7594-48a7-8688-d537ea6f7c18 · outbound
This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.877252Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0b2320a8-d09f-4b73-8953-30b083ddc985 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 47
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-07T05:36:58.862074Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0854fd31-d5f6-4687-81c9-55f03057c7a1 · outbound
This paper cites GPT-4 Technical Report.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts GPT-4 Technical Report
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.047377Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 09546edd-6355-4941-9fbd-550e64cccb87 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 49
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:58.847174Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 1dc111cf-1c33-438d-9d62-2d807d3fca6a · outbound
This paper cites Automated Red Teaming with GOAT: the Generative Offensive Agent Tester.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.057842Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1fd41837-867c-4e8b-9394-03d60eb485a8 · outbound
This paper cites Gradient Descent.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gradient Descent
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.830890Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation ed92a7e7-6207-4378-b555-6d3d17790395 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 52
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:58.814992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 56c857bd-92be-4fc8-ae18-dda51f1f0073 · outbound
This paper cites The Llama 3 Herd of Models.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts The Llama 3 Herd of Models
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.072430Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fd0fe736-56e2-4922-9f49-3afeba09c9cc · outbound
This paper cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale.AAAI, 2020.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts WinoGrande: An Adversarial Winograd Schema Challenge at Scale.AAAI, 2020
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.800197Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 6a8ebfe2-3fcc-4bb2-be3f-749b3a309df3 · outbound
This paper cites Neural Machine Translation of Rare Words with Sub- word Units.ACL, 2016.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Neural Machine Translation of Rare Words with Sub- word Units.ACL, 2016
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.785772Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c88a7991-a998-4bd2-bcc7-971a4a59e63b · outbound
This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.086467Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dd6b4dc9-8314-4cda-85af-50ffce4abdf8 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 57
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:58.770882Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 67c4dc04-fa81-445b-a13e-1a5e73ed3713 · outbound
This paper cites Gemma, 2024.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gemma, 2024
Reference 58
- Resolution
- parse uncertain
- no resolver link, observed 2026-08-07T05:36:58.095917Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fbdaf693-0569-42be-84f7-2153f8c0e3c8 · outbound
This paper cites Gemma 3, 2025.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Gemma 3, 2025
Reference 59
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.100779Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b1d25097-5d47-4f4f-b981-161f50c9f53d · outbound
This paper cites Pytorch, 2022.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Pytorch, 2022
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.737769Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c603f4e8-17d7-4a05-89c1-5945d2ef7818 · outbound
This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.110690Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c1526ad-f5be-484f-98e7-2573dd02add4 · outbound
This paper cites Centrum voor Wiskunde en Informatica Amsterdam, 1995.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Centrum voor Wiskunde en Informatica Amsterdam, 1995
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.724100Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation a18405a5-5cfc-4230-9522-61f54cb7fb90 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 63
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:58.708640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 36195b31-1a83-48f9-9e28-ac244d5ee814 · outbound
This paper cites A Simple and Effective Pruning Approach for Large Language Models.ICLR, 2024.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts A Simple and Effective Pruning Approach for Large Language Models.ICLR, 2024
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.694479Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 5dd3082f-e0aa-48dd-a03a-1d576f8b1046 · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 65
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:58.680727Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation abd6921c-f91f-4c0e-b1af-47bf8baa381a · outbound
This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.135736Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fc70e041-e9e1-4943-9760-4bb594bbb20a · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 67
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:58.665664Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 7b986524-8426-48e8-97f4-b410817e86b7 · outbound
This paper cites Qwen2 Technical Report.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Qwen2 Technical Report
Reference 68
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.144812Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b633371f-6db0-4379-ac16-8d75271362fb · outbound
This paper cites an unresolved cited work.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Unresolved cited work
Reference 69
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:36:58.650035Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation e7482177-de9c-4389-931c-da572ce734cc · outbound
This paper cites NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning.AAAI, 2025.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning.AAAI, 2025
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.635315Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 1286cca4-608d-45a7-baef-af7346ed68bf · outbound
This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Reference 71
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:36:58.160681Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3cb4a1b2-dfd7-4561-9f38-162b82ca55fc · outbound
This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?ACL, 2019.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts HellaSwag: Can a Machine Really Finish Your Sentence?ACL, 2019
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.621030Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 09e75c66-8e2c-4d85-b9a2-3bdd3d676cf6 · outbound
This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.ACL ARR, 2024.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.ACL ARR, 2024
Reference 73
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.606730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation daac7867-7860-4232-906f-d8f9a0e09b22 · outbound
This paper cites Understanding and Enhancing Safety Mechanisms of LLMs via Safety- Specific Neuron.ICLR, 2025.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Understanding and Enhancing Safety Mechanisms of LLMs via Safety- Specific Neuron.ICLR, 2025
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:36:58.590629Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation cf19b872-e853-43ed-807b-73791d8b8c34 · outbound
This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 75
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-07T05:36:58.179549Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 05abea8d-e50b-41c8-97f6-31c40d0436e9 · inbound
GoodVibe: Security-by-Vibe for LLM-Based Code Generation cites this paper.
GoodVibe: Security-by-Vibe for LLM-Based Code Generation TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T01:03:28.012736Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e5ecc3ab-046e-43dd-a0ba-16e046acb8c0 · inbound
The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring cites this paper.
The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T02:46:18.596218Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.