Paper Citation Record · LEDGER

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 40 inbound Pith citation observations for arXiv:2405.21018.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2405.21018 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 40 of 40 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:00:26.622586Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-10T11:57:03.497396Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 7c858d35-d181-418c-8c9d-c5b3bb8c5f06 · inbound

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models cites this paper.

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-23T19:03:21.364237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 87431442-4a21-45d2-975b-0dea9be7aa07 · inbound

Global Challenge for Safe and Secure LLMs Track 1 cites this paper.

Global Challenge for Safe and Secure LLMs Track 1 Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T15:48:29.463003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46fa5736-a598-4b43-9831-38896a57a666 · inbound

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models cites this paper.

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:17:02.657488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c367882-5566-4d4f-baab-1155ff1a9ef4 · inbound

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks cites this paper.

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T19:08:01.645564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f9ccf32-212f-4d7d-947e-5640cf04e12d · inbound

Adversarial Reasoning at Jailbreaking Time cites this paper.

Adversarial Reasoning at Jailbreaking Time Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T14:49:08.746274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fb65307-e2e1-4b9c-a6f2-7a32e13f3fd1 · inbound

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety cites this paper.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 94

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.240968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 305bb6c3-83a5-4452-8785-4ab3efbffebf · inbound

LLM-Safety Evaluations Lack Robustness cites this paper.

LLM-Safety Evaluations Lack Robustness Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-23T01:27:21.293947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b1c3a59b-97ef-495c-9b59-b656b2d39a48 · inbound

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems cites this paper.

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T15:21:44.807132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8729fdfa-68d5-4471-96b8-893b157485b5 · inbound

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval cites this paper.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.626254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49614ecf-7ebe-4437-822e-8195123ddfda · inbound

Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers cites this paper.

Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:08:11.240128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 918cc513-33f3-4b45-aa54-b057d3f459f3 · inbound

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs cites this paper.

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:48:16.511497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81f2ac65-f37e-4834-a20f-65676620ad65 · inbound

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space cites this paper.

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:35:56.893528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72aa392a-d53a-4eb3-8989-88f9158796ad · inbound

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures cites this paper.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.616360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97915f6a-f7a7-4460-9899-dcd2cf9cb3ee · inbound

When Meaning Stays the Same, but Models Drift: Evaluating Quality of Service under Token-Level Behavioral Instability in LLMs cites this paper.

When Meaning Stays the Same, but Models Drift: Evaluating Quality of Service under Token-Level Behavioral Instability in LLMs Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:42:18.651102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2bfecdd-1356-4824-8494-fac5065e7174 · inbound

SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models cites this paper.

SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T23:20:56.482120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6126766f-69e0-4b9e-9aca-6659cfef3d70 · inbound

VERA: Variational Inference Framework for Jailbreaking Large Language Models cites this paper.

VERA: Variational Inference Framework for Jailbreaking Large Language Models Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T22:07:03.636792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1961d8ca-26d2-449c-aedb-debd7b08be4b · inbound

Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation cites this paper.

Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T18:00:26.622586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6265bbc8-9c57-46f2-b42d-6d9d0eb65852 · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.703450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bff3f494-da51-43f4-aae2-dc5a9db4d427 · inbound

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? cites this paper.

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T16:00:48.580403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e212b26f-8e30-49ac-9c05-5609c0488114 · inbound

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks? cites this paper.

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks? Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T23:49:31.864821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9fd3744-54fb-4e18-865c-2d0705289715 · inbound

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents cites this paper.

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T21:44:12.308523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fc8e22e-06f5-4508-a2f6-6ce594fdee4a · inbound

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents cites this paper.

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:50:09.389631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fda6857d-5cd5-41c2-ad21-4101d0f7f0bb · inbound

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents cites this paper.

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T23:20:42.271415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74418ef4-c29e-4c97-89c6-72bb5cfa9d5e · inbound

JailWAM: Jailbreaking World Action Models in Robot Control cites this paper.

JailWAM: Jailbreaking World Action Models in Robot Control Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:05:48.158122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aa49575c-44d1-48f0-8317-deb12786cfca · inbound

Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion cites this paper.

Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:46:04.345513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 00c1cd55-515c-4691-b73f-f1b158fae6f0 · inbound

Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries cites this paper.

Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T08:53:04.235190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5b830efd-980d-40cd-9118-6bcb01b3df15 · inbound

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements cites this paper.

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-13T22:03:20.495617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ef4f7c10-ea02-477d-91a9-a7035b603f47 · inbound

Jailbreaking Frontier Foundation Models Through Intention Deception cites this paper.

Jailbreaking Frontier Foundation Models Through Intention Deception Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:11:13.991238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0b3429e7-4997-46b0-8b8d-c869e6211d78 · inbound

Attention Is Where You Attack cites this paper.

Attention Is Where You Attack Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:31:05.208137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f80b07dc-7d32-49e8-a18e-cd4be1f4a5f1 · inbound

Adversarial Reframing: A Framework for Targeted Generation in Language Models cites this paper.

Adversarial Reframing: A Framework for Targeted Generation in Language Models Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T09:36:21.033098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 86bb73dd-a8da-453c-aaea-441cff595146 · inbound

CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning cites this paper.

CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:23:15.757226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cfd9c796-3e0b-436e-b081-d22582f3da6b · inbound

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks cites this paper.

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 40

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:26:59.243117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 64eae4ca-83f3-40f2-8dcf-582661559c94 · inbound

Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance cites this paper.

Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 49

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:08:43.447341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e5c55392-893c-474c-9976-872d14f5395a · inbound

FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming cites this paper.

FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-04T04:09:34.754405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8a15a320-d194-4edd-94f4-015f833f2e53 · inbound

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation cites this paper.

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T19:50:11.159040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6b83f89d-0a1c-4230-84be-d0a45d9a07bc · inbound

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation cites this paper.

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T10:16:39.061069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a54c2a52-a9cd-497d-afa7-33e08bda3492 · inbound

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions cites this paper.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.110965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2023757d-8547-4eb2-9be1-263013a88a7a · inbound

Out of Sight: Compression-Aware Content Protection against Agentic Crawlers cites this paper.

Out of Sight: Compression-Aware Content Protection against Agentic Crawlers Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 46

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T11:57:03.498966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ee5f4810-1ec9-4d50-b3aa-eebb2220b798 · inbound

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions cites this paper.

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T18:54:55.306378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56995e29-896a-454b-8308-91998213f5b1 · inbound

ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners cites this paper.

ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T11:52:15.946807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.