Paper Citation Record · LEDGER

NonTextual Target Attack

As of 15 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 5 inbound Pith citation observations for arXiv:2510.02999.

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

pith.paper-citation-record.v1
2510.02999 v5

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T12:44:04.461847Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T20:49:20.247547Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 82f96f9a-b0a9-4f8f-ac2d-7706310b02d7 · outbound

This paper cites write newline.

NonTextual Target Attack write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:01.737579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8c0db2f-5f99-4ce6-aee7-d9bdc022b6e6 · outbound

This paper cites Detecting language model attacks with perplexity, 2023.

NonTextual Target Attack Detecting language model attacks with perplexity, 2023

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:01.801628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbf97da5-0632-4a24-b406-ea975802cafa · outbound

This paper cites Jailbreaking leading safety-aligned llms with simple adaptive attacks, 2025.

NonTextual Target Attack Jailbreaking leading safety-aligned llms with simple adaptive attacks, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:01.838175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e7b09f-f16f-44a9-bf22-7d086c6f9127 · outbound

This paper cites When llm meets drl: Advancing jailbreaking efficiency via drl-guided search, 2025.

NonTextual Target Attack When llm meets drl: Advancing jailbreaking efficiency via drl-guided search, 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:01.853490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0655558e-3480-4fac-8b8a-c19c5d93c94a · outbound

This paper cites The llama 3 herd of models, 2024.

NonTextual Target Attack The llama 3 herd of models, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:01.906304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65e9bb05-6045-47f1-947a-ed2c986149ff · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

NonTextual Target Attack DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:01.973418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f85f29fa-0e5a-4a00-9619-75833c22f9b9 · outbound

This paper cites COLD -attack: Jailbreaking LLM s with stealthiness and controllability.

NonTextual Target Attack COLD -attack: Jailbreaking LLM s with stealthiness and controllability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.127701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5e43586-68ea-4a67-8ec3-00cd0cc12845 · outbound

This paper cites Dualbreach: Efficient dual-jailbreaking via target-driven initialization and multi-target optimization, 2025.

NonTextual Target Attack Dualbreach: Efficient dual-jailbreaking via target-driven initialization and multi-target optimization, 2025

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.271719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f93b502-44bc-4e6f-83d2-814a79c7a246 · outbound

This paper cites Baseline defenses for adversarial attacks against aligned language models, 2023.

NonTextual Target Attack Baseline defenses for adversarial attacks against aligned language models, 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.387598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff08df8-39aa-41d5-b004-62c15b0ab9fb · outbound

This paper cites Improved techniques for optimization-based jailbreaking on large language models, 2024.

NonTextual Target Attack Improved techniques for optimization-based jailbreaking on large language models, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.442919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bfc140f-61b2-4c86-86fb-b6828864a443 · outbound

This paper cites Mistral 7B.

NonTextual Target Attack Mistral 7B

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.493204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dba98d0-cf5b-4e8a-99c1-a17eb67de622 · outbound

This paper cites Amplegcg: Learning a universal and transferable generative model of adversarial suffixes for jailbreaking both open and closed llms, 2024.

NonTextual Target Attack Amplegcg: Learning a universal and transferable generative model of adversarial suffixes for jailbreaking both open and closed llms, 2024

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.560937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58e52490-cba5-4881-a061-cd720e76e114 · outbound

This paper cites Advancing adversarial suffix transfer learning on aligned large language models, 2024 a.

NonTextual Target Attack Advancing adversarial suffix transfer learning on aligned large language models, 2024 a

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.617654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44b3c29d-f3e4-46b4-8285-6587885d555d · outbound

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

NonTextual Target Attack Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.722697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cd4317f-86a4-4275-8337-adf3c5de1c7a · outbound

This paper cites Harmbench: a standardized evaluation framework for automated red teaming and robust refusal.

NonTextual Target Attack Harmbench: a standardized evaluation framework for automated red teaming and robust refusal

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.854141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e3f272-3013-4265-819e-714de8ba0ef3 · outbound

This paper cites Language models are unsupervised multitask learners.

NonTextual Target Attack Language models are unsupervised multitask learners

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:02.945466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99627969-14ce-4bd0-b05e-fe0ea133414e · outbound

This paper cites an unresolved cited work.

NonTextual Target Attack Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.057308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32d837dd-7eaa-4fe7-8d42-732477ff0ded · outbound

This paper cites do anything now.

NonTextual Target Attack do anything now

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.124554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7806188e-7aba-43ba-b7d4-a4f9f494df4e · outbound

This paper cites Dynamic target attack, 2025.

NonTextual Target Attack Dynamic target attack, 2025

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.210753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b17adb40-a580-4eb9-9260-f52588f8032d · outbound

This paper cites Qwen2 technical report, 2024.

NonTextual Target Attack Qwen2 technical report, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.321275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 619c801a-228a-4d86-9dfc-d5b11d3d7384 · outbound

This paper cites Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts, 2024.

NonTextual Target Attack Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts, 2024

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.446300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92389e98-7191-44e0-a0a7-55c69ca94434 · outbound

This paper cites How johnny can persuade LLM s to jailbreak them: Rethinking persuasion to challenge AI safety by humanizing LLM s.

NonTextual Target Attack How johnny can persuade LLM s to jailbreak them: Rethinking persuasion to challenge AI safety by humanizing LLM s

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.545057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a48dec15-8ace-45e8-854b-6c682d6fe931 · outbound

This paper cites A survey of large language models, 2024.

NonTextual Target Attack A survey of large language models, 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.688438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4366f98-df0b-4921-9643-28e5a42d7dde · outbound

This paper cites Xing, Hao Zhang, Joseph E.

NonTextual Target Attack Xing, Hao Zhang, Joseph E

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.750088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3904a3b-a2ad-48a4-8344-8b8da8182906 · outbound

This paper cites Don't say no: Jailbreaking llm by suppressing refusal, 2024.

NonTextual Target Attack Don't say no: Jailbreaking llm by suppressing refusal, 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.877815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf7c6c90-be23-4f6a-ac7c-75d7edf1e75e · outbound

This paper cites Advprefix: An objective for nuanced llm jailbreaks, 2024.

NonTextual Target Attack Advprefix: An objective for nuanced llm jailbreaks, 2024

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:03.993700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 333e0d5b-f6d2-40cd-b99a-810623c48468 · outbound

This paper cites Zico Kolter, and Matt Fredrikson.

NonTextual Target Attack Zico Kolter, and Matt Fredrikson

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:04.106273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcd6837f-5457-4384-a74a-a6b412d7e5da · outbound

This paper cites @esa (Ref.

NonTextual Target Attack @esa (Ref

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:04.216844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35a50faf-5cfd-4624-b20b-e546bc9580f5 · outbound

This paper cites an unresolved cited work.

NonTextual Target Attack Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:04.364109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 846fbc99-492c-400e-a1ed-32a4121e9599 · outbound

This paper cites an unresolved cited work.

NonTextual Target Attack Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:04.461847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ab0e3d04-815c-404d-a926-28f32950a061 · inbound

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization cites this paper.

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization NonTextual Target Attack

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-09T01:19:04.946819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4d471524-fb69-49e7-a637-52a4588d4159 · inbound

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization cites this paper.

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization NonTextual Target Attack

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-09T01:19:04.946819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ca9c06c3-4896-4420-bc99-9c0576a0a024 · inbound

RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry cites this paper.

RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry NonTextual Target Attack

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-09T01:19:04.946819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e8aaf750-6a18-4fec-9160-935d9589216e · inbound

DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection cites this paper.

DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection NonTextual Target Attack

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T11:40:26.849024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3717779-6bdb-480c-86bb-46559091b8f2 · inbound

ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions cites this paper.

ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions NonTextual Target Attack

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-12T20:49:20.247547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.