Paper Citation Record · LEDGER

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 26 inbound Pith citation observations for arXiv:2302.05733.

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

pith.paper-citation-record.v1
2302.05733 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 26 of 26 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:18:09.749817Z

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

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

27
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 40842c4f-588b-44d0-85a7-b46df7e64d03 · inbound

Jailbroken: How Does LLM Safety Training Fail? cites this paper.

Jailbroken: How Does LLM Safety Training Fail? Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:17:42.855510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 890a477b-2c06-42aa-b0c7-c603ae315350 · inbound

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models cites this paper.

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-17T08:39:28.174978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 72287e84-52b2-4c64-83c7-763383e4bd24 · inbound

Baseline Defenses for Adversarial Attacks Against Aligned Language Models cites this paper.

Baseline Defenses for Adversarial Attacks Against Aligned Language Models Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-13T23:24:40.023866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dec75bb5-f715-4e46-a240-8010246d6287 · inbound

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models cites this paper.

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-12T16:28:04.062859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5ca57504-058d-4863-8fff-5f7e9942d0d9 · inbound

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation cites this paper.

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:00:51.556822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8f19794a-fcc9-4122-ac96-88a49465957f · inbound

Whispers in the Machine: Confidentiality in Agentic Systems cites this paper.

Whispers in the Machine: Confidentiality in Agentic Systems Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-24T04:03:53.849912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a1aa8d47-9e09-4692-b3f3-498a0ada33ba · inbound

A StrongREJECT for Empty Jailbreaks cites this paper.

A StrongREJECT for Empty Jailbreaks Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-16T21:28:02.825041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 83ea2ea0-dc41-4608-8feb-36b8746ef217 · inbound

LLM Agents can Autonomously Exploit One-day Vulnerabilities cites this paper.

LLM Agents can Autonomously Exploit One-day Vulnerabilities Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-18T04:18:27.709259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation db4aa327-8f7b-4cc0-938c-63201fa0ad10 · inbound

Jailbreak Attacks and Defenses Against Large Language Models: A Survey cites this paper.

Jailbreak Attacks and Defenses Against Large Language Models: A Survey Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:20:44.691880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d826b6f6-c434-4f2f-9f3c-ebcb4d31cbff · inbound

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems cites this paper.

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:32:19.734280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 87dea015-967a-41c4-b047-429f37b479c2 · 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 Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-23T19:03:21.401463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8be6a381-9282-4a32-91b1-c9e44092809c · inbound

Next-Generation Phishing: How LLM Agents Empower Cyber Attackers cites this paper.

Next-Generation Phishing: How LLM Agents Empower Cyber Attackers Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T15:51:08.507906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7199547d-18f7-4a79-b89a-c7b80e5a94e6 · inbound

Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks cites this paper.

Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T20:18:09.749817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87c3da8a-2bd1-4af8-98b4-e89550e2d730 · inbound

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation cites this paper.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.657815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503994c0-873c-4d01-bc23-7d6f96f3ef5c · inbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.107700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6857368-c41a-444e-9b2e-866c399a234a · inbound

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring cites this paper.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.693056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f0c4c94-9fea-4cec-b91e-ed6b9cb57b4e · inbound

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs cites this paper.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:27.941873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3540126a-5c94-4b96-a78e-565f1ab7fa6f · inbound

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint cites this paper.

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T23:10:21.297410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efbff674-42ba-4754-b406-ece032bb95c6 · inbound

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security cites this paper.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.524212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d508c59e-88d6-4476-ab2e-39b72eba5cac · inbound

Stop Testing Attacks, Start Diagnosing Defenses: The Four-Checkpoint Framework Reveals Where LLM Safety Breaks cites this paper.

Stop Testing Attacks, Start Diagnosing Defenses: The Four-Checkpoint Framework Reveals Where LLM Safety Breaks Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T02:51:56.253042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1160e7af-8cad-404a-a8de-db28bcebb7d5 · inbound

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code cites this paper.

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:56:26.794119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ed14cc08-8635-43ca-add9-8f1e6044f166 · inbound

Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking cites this paper.

Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:31:06.043863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a2877a87-885f-4c60-b65a-24eb260debe9 · inbound

Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion cites this paper.

Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:59:58.296057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a0791066-8569-4077-912c-6a9276d55ff4 · inbound

Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense cites this paper.

Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 107

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T12:45:44.893381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6b1f1121-dc29-424d-8748-8d7fa42f2719 · inbound

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems cites this paper.

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-01T11:05:42.347271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9d2ee81b-6ff7-4404-86db-19c084bdfc09 · inbound

RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation cites this paper.

RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T08:37:33.396857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.