MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment | Paper Citation Record

Observation 75627284-cba0-49fa-9765-ef99ddcdaaa6 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99334c41-7d36-4629-a9e8-26ed42d64bd4 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b model card, 2025.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment gpt-oss-120b & gpt-oss-20b model card, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ab60739-ed5f-4647-8b0b-701920739dc4 · outbound

This paper cites Introducing GPT-5.5.https://openai.com/index/introducing-gpt-5-5/, Apr 2026.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Introducing GPT-5.5.https://openai.com/index/introducing-gpt-5-5/, Apr 2026

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f6e9e38-4af1-4db3-8774-cb3d2e7ab02d · outbound

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

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b56c0b96-e27a-4bfc-aadc-522f3e0a609f · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb3cf4c7-95fc-4193-aaeb-7263af349c06 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69a1f2fe-5512-4629-9225-7c3bfa4867d0 · outbound

This paper cites Red teaming language models with language models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Red teaming language models with language models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57a56e25-6265-40b8-acf0-083a25419598 · outbound

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

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Jailbreaking black box large language models in twenty queries

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 099b3a8c-649b-4f9d-9b7f-a34b23df693e · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically.Ad- vances in Neural Information Processing Systems, 37:61065–61105, 2024.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Tree of attacks: Jailbreaking black-box llms automatically.Ad- vances in Neural Information Processing Systems, 37:61065–61105, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76b5ab4e-8bde-432a-ba0d-041160a26e02 · outbound

This paper cites SEMA: Simple yet effective learning for multi-turn jailbreak attacks.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment SEMA: Simple yet effective learning for multi-turn jailbreak attacks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 540b64e0-bef0-4d14-8557-790ca54a0bb4 · outbound

This paper cites TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62146656-85ba-4c8c-84a4-d3c713cab06b · outbound

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

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2930384-279f-483e-ba17-0670c1cf5647 · outbound

This paper cites Artprompt: Ascii art-based jailbreak attacks against aligned llms.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Artprompt: Ascii art-based jailbreak attacks against aligned llms

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c924c766-0fff-4089-bc51-820a0c437c3d · outbound

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

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04cd8e83-9f86-4af1-8df9-7fa84e9c6a8f · outbound

This paper cites Flipattack: Jailbreak LLMs via flipping.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Flipattack: Jailbreak LLMs via flipping

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3c9c848-d28c-4c28-9654-912a3ac4bf48 · outbound

This paper cites Speak easy: Eliciting harm- ful jailbreaks from LLMs with simple interactions.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Speak easy: Eliciting harm- ful jailbreaks from LLMs with simple interactions

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94ee47b2-b50c-4fdd-a961-053927ba8ee8 · outbound

This paper cites How johnny can persuade LLMs to jailbreak them: Rethinking persuasion to challenge AI safety by human- izing LLMs.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment How johnny can persuade LLMs to jailbreak them: Rethinking persuasion to challenge AI safety by human- izing LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2016a724-d59c-447f-857a-2ce86d0f7c72 · outbound

This paper cites A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aecddda-aa70-4e50-a9aa-fdfa9f886475 · outbound

This paper cites Best-of-n jailbreaking.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Best-of-n jailbreaking

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6a692c9-4c74-4e58-b463-52010010949e · outbound

This paper cites Jailbreaking leading safety-aligned LLMs with simple adaptive attacks.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Jailbreaking leading safety-aligned LLMs with simple adaptive attacks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5319c34-5376-4b10-a9b0-e155eaa20c79 · outbound

This paper cites One model transfer to all: On robust jailbreak prompts generation against LLMs.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment One model transfer to all: On robust jailbreak prompts generation against LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43f35c2c-8b6d-40a6-a9bf-ef446b7155d1 · outbound

This paper cites AutoDAN: Automatic and interpretable adversarial attacks on large language models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment AutoDAN: Automatic and interpretable adversarial attacks on large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 630c0e51-fd70-417a-a3ae-03b3f126c7ff · outbound

This paper cites Markosyan, Manish Bhatt, Yuning Mao, Minqi Jiang, Jack Parker-Holder, Jakob Nicolaus Foerster, Tim Rocktäschel, and Roberta Raileanu.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Markosyan, Manish Bhatt, Yuning Mao, Minqi Jiang, Jack Parker-Holder, Jakob Nicolaus Foerster, Tim Rocktäschel, and Roberta Raileanu

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8ab7de0-ef03-447a-9f60-7378374f6c54 · outbound

This paper cites Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 179e9f51-b47b-43ad-ba00-b16c0275e98f · outbound

This paper cites Glass, Akash Srivastava, and Pulkit Agrawal.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Glass, Akash Srivastava, and Pulkit Agrawal

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 442a5668-d392-4cea-b4db-13c4f356a6db · outbound

This paper cites Edward Suh, Yevgeniy V orobeychik, Zhuoqing Mao, Somesh Jha, Patrick McDaniel, Huan Sun, Bo Li, and Chaowei Xiao.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Edward Suh, Yevgeniy V orobeychik, Zhuoqing Mao, Somesh Jha, Patrick McDaniel, Huan Sun, Bo Li, and Chaowei Xiao

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3f95b79-91ea-474c-ad42-5cfa84f59951 · outbound

This paper cites Auto-RT: Automatic jailbreak strategy exploration for red-teaming large language models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Auto-RT: Automatic jailbreak strategy exploration for red-teaming large language models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d982b5c-ca78-455f-b26b-47ae1200011b · outbound

This paper cites Align to misalign: Automatic LLM jailbreak with meta-optimized LLM judges.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Align to misalign: Automatic LLM jailbreak with meta-optimized LLM judges

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15565a68-1083-461c-81db-9e8a5499d2a3 · outbound

This paper cites Autoredteamer: Autonomous red teaming with lifelong attack integration.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Autoredteamer: Autonomous red teaming with lifelong attack integration

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65d0082-8d23-43e1-a3fb-020b81af4227 · outbound

This paper cites Cop: Agentic red-teaming for large language models using composition of principles.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Cop: Agentic red-teaming for large language models using composition of principles

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d07cedf-b296-4e37-bbf6-2d4bbee7f8a0 · outbound

This paper cites Great, now write an article about that: The crescendo{Multi-Turn}{LLM}jailbreak attack.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Great, now write an article about that: The crescendo{Multi-Turn}{LLM}jailbreak attack

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14d4f9cb-2df1-4470-88e3-e0433e961e70 · outbound

This paper cites Foot-in-the-door: A multi-turn jailbreak for LLMs.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Foot-in-the-door: A multi-turn jailbreak for LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 565d3a4a-2229-45ef-97af-764ea73e5ab1 · outbound

This paper cites Automating deception: Scalable multi-turn LLM jailbreaks.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Automating deception: Scalable multi-turn LLM jailbreaks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43de3537-73e8-472b-910c-e99f1acb61d4 · outbound

This paper cites Automated red teaming with goat: the generative offensive agent tester.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Automated red teaming with goat: the generative offensive agent tester

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37bca848-a1d5-4485-9d47-ab9f8c09e1c9 · outbound

This paper cites Chain of attack: Hide your intention through multi-turn interrogation.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Chain of attack: Hide your intention through multi-turn interrogation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e1c801-f7ab-437e-8a35-abbbf8e7c8fd · outbound

This paper cites Reasoning-augmented conversa- tion for multi-turn jailbreak attacks on large language models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Reasoning-augmented conversa- tion for multi-turn jailbreak attacks on large language models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a813f3b-2758-4e56-9dfc-160b593948b8 · outbound

This paper cites an unresolved cited work.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00ad9553-9e02-443c-8179-b9c2a1595d69 · outbound

This paper cites Analogy-based multi-turn jailbreak against large language models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Analogy-based multi-turn jailbreak against large language models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf06ec57-99ed-4f09-9779-f3d9ca9753ed · outbound

This paper cites X-teaming: Multi-turn jail- breaks and defenses with adaptive multi-agents.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment X-teaming: Multi-turn jail- breaks and defenses with adaptive multi-agents

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aea29c60-c389-46d9-9dd4-16f45bef5db6 · outbound

This paper cites LLMs know their vulnerabilities: Uncover safety gaps through natural distribution shifts.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment LLMs know their vulnerabilities: Uncover safety gaps through natural distribution shifts

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52733078-96c1-4020-a2d5-e009ce5adfc8 · outbound

This paper cites Siren: A learning-based multi-turn attack framework for simulating real-world human jailbreak behaviors.arXiv preprint arXiv:2501.14250, 2025.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Siren: A learning-based multi-turn attack framework for simulating real-world human jailbreak behaviors.arXiv preprint arXiv:2501.14250, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4109c34c-0729-41ba-b748-7b5213112bad · outbound

This paper cites Mtsa: Multi- turn safety alignment for llms through multi-round red-teaming.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Mtsa: Multi- turn safety alignment for llms through multi-round red-teaming

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3027b367-7782-4403-b2e0-6f16e831840e · outbound

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

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Direct preference optimization: Your language model is secretly a reward model

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a46ca6f2-e79f-44a6-bb73-5c16bf525908 · outbound

This paper cites Reinforcing multi-turn reasoning in LLM agents via turn-level credit as- signment.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Reinforcing multi-turn reasoning in LLM agents via turn-level credit as- signment

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbe6e299-8047-40c1-8fac-34deac5f1d66 · outbound

This paper cites Proximal Policy Optimization Algorithms.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Proximal Policy Optimization Algorithms

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee94b289-9ebd-4312-b7d3-dd845e61652f · outbound

This paper cites Proximity-based multi-turn optimization: Practical credit assignment for llm agent training.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Proximity-based multi-turn optimization: Practical credit assignment for llm agent training

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e42606bf-c452-4d3f-8e24-b4b133bb4800 · outbound

This paper cites Group-in-group policy optimization for LLM agent training.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Group-in-group policy optimization for LLM agent training

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48466b91-2208-41a9-8a87-d3681059310c · outbound

This paper cites Hierarchy-of-groups policy optimization for long-horizon agentic tasks.arXiv preprint arXiv:2602.22817, 2026.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Hierarchy-of-groups policy optimization for long-horizon agentic tasks.arXiv preprint arXiv:2602.22817, 2026

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36a7aa5d-647f-47a2-9422-9dd5391e664a · outbound

This paper cites Zico Kolter, and Matt Fredrikson.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Zico Kolter, and Matt Fredrikson

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bddeb17c-38e2-4b03-9e6a-964a706cb454 · outbound

This paper cites do anything now.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment do anything now

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce3c5ec9-d377-4623-bc8a-18a590665f81 · outbound

This paper cites M2s: Multi-turn to single-turn jailbreak in red teaming for llms.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment M2s: Multi-turn to single-turn jailbreak in red teaming for llms

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8994fe59-35a0-4981-816a-349faf59a0b0 · outbound

This paper cites Qwen3 technical report, 2025.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Qwen3 technical report, 2025

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a02b8cd-c06d-4779-a0ce-b6b4de411bed · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Qwen2.5: A party of foundation models, September 2024

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32e892a8-4f2f-4f63-ac91-31313bd0b87b · outbound

This paper cites Qwen2 Technical Report.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Qwen2 Technical Report

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f952dcd6-f016-44ff-ae39-ee164177ac40 · outbound

This paper cites The Llama 3 Herd of Models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment The Llama 3 Herd of Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c141f65-935e-4ec6-980d-0bf03fc308ec · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Gemma 2: Improving Open Language Models at a Practical Size

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ed7f000-c001-4849-827d-bc41319318cd · outbound

This paper cites Mistral 7B.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Mistral 7B

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b7e8732-b495-48ad-bfd8-cb0bf3f02011 · outbound

This paper cites Qwen3Guard Technical Report.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Qwen3Guard Technical Report

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 779f2060-ec53-4f84-b2b6-51a503404d28 · outbound

This paper cites Harm- bench: A standardized evaluation framework for automated red teaming and robust refusal.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Harm- bench: A standardized evaluation framework for automated red teaming and robust refusal

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3ccbd8f-88df-4f01-b4a4-1ee8d7ec5b02 · outbound

This paper cites Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of LLMs.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of LLMs

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 638285e5-2e89-4091-b854-4ab15605af96 · outbound

This paper cites A strongREJECT for empty jailbreaks.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment A strongREJECT for empty jailbreaks

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ab44193-baba-44a5-b4ba-e56dc48ea8aa · outbound

This paper cites Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0b4e2eb-357b-4a8e-a00e-b62f21ddc617 · outbound

This paper cites Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c1d198-2be0-4ef8-acd0-8447c2bae67d · outbound

This paper cites Introducing gpt-4.1 in the api.https://openai.com/index/gpt-4-1/, April.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Introducing gpt-4.1 in the api.https://openai.com/index/gpt-4-1/, April

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4e66740-80ed-48e6-93d1-7f4e0a3bb730 · outbound

This paper cites an unresolved cited work.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Unresolved cited work

Reference 65

Resolution: parse uncertain; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b27e27-1bb9-412d-b83e-a6d2f28cbdec · outbound

This paper cites Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8eb20657-8025-43fa-a968-3b56aca3c8fe · outbound

This paper cites Safety alignment should be made more than just a few tokens deep.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Safety alignment should be made more than just a few tokens deep

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35da2263-e7bc-485f-9272-026ad5e2bb6a · outbound

This paper cites Post-training large language models for diverse high-quality responses.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Post-training large language models for diverse high-quality responses

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32c6562c-4593-4dd6-a225-ecb1b447d1ba · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Deepseek-v4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa7b91ca-3973-4743-ac4e-48e6ba9e7bad · outbound

This paper cites A successful first turn sets up everything.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment A successful first turn sets up everything

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5eb93f-4dcb-4376-a380-ea9194c4d5f1 · outbound

This paper cites an unresolved cited work.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Unresolved cited work

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9082aed-a092-4ec6-aa85-26700f39d25d · outbound

This paper cites Write instructions for X.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Write instructions for X

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50097cfd-c3cf-479d-940e-08189ca38d20 · outbound

This paper cites Fake", "Fictional.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Fake", "Fictional

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90e27790-da79-4aa4-a914-6ca1318dc078 · outbound

This paper cites No brackets explaining it's fake.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment No brackets explaining it's fake

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6be3417d-6b24-4a48-abe3-b118420b01e5 · outbound

This paper cites yes" or.

MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment yes" or

Reference 75

Resolution: malformed identifier; no resolver link, observed 2026-07-14T07:16:57.009797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers