Pith. sign in

Paper Citation Record · LEDGER

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 17 inbound Pith citation observations for arXiv:2505.04806.

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

pith.paper-citation-record.v1
2505.04806 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:25:42.450138Z

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

0
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 04941d1a-7427-48ec-a832-4c17fd59af40 · inbound

Exposing Hidden Backdoors in NFT Smart Contracts: A Static Security Analysis of Rug Pull Patterns cites this paper.

Exposing Hidden Backdoors in NFT Smart Contracts: A Static Security Analysis of Rug Pull Patterns Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:42.450138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:42.450138Z digest=sha256:91f300f52eb48f8622909a6c43a81c6db0e8e7c543e18203531c5f3c7d78fcfa

Observation b4282a96-6bb9-4961-b94c-0cb55c1f85d4 · inbound

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents cites this paper.

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 99

Resolution
unresolved
no resolver link, observed 2026-08-06T21:34:45.015831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:34:45.015831Z digest=sha256:f357863468cf636d07be60bb9e44d4895943b8b889d71fb4b716c736bfd9114f

Observation f06f63dd-10ab-4e04-a6d4-df2ba5aebb24 · inbound

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking cites this paper.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T19:56:05.267094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T19:56:05.267094Z digest=sha256:7f2e2dd62a9bf7ba136ef86a3dce9a22f885f6da925424390323049049e71f54

Observation f9984e62-8605-4ef4-8134-5a73f9b6d88a · inbound

ANNIE: Be Careful of Your Robots cites this paper.

ANNIE: Be Careful of Your Robots Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-05T11:00:38.221707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T11:00:38.221707Z digest=sha256:f7dbb27af8ff7be9c82f8c1013790e7710c060351e87c3473d443e49b2c8310f

Observation 4915318a-e3b8-4ea4-8341-f944fe4a7c5b · inbound

Beyond Context: Large Language Models' Failure to Grasp Users' Intent cites this paper.

Beyond Context: Large Language Models' Failure to Grasp Users' Intent Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 48

Resolution
metadata mismatch
arxiv_id, observed 2026-05-16T20:11:13.575849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-16T20:09:25.827452Z digest=sha256:14913e5398799ce1053d10ede93e8e98473427cf7cbde744fa8f516d45ec56b2

Observation 267ac4c7-1726-48ad-87cc-fe52b623d097 · inbound

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection cites this paper.

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 10

Resolution
metadata mismatch
arxiv_id, observed 2026-05-21T15:20:17.397162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-21T15:18:58.274360Z digest=sha256:ad4fd0e8f1a938619647c775ab7a4f73d4b980f4691c6037b6c684079f367e99

Observation acb0caf6-b910-471d-bc89-14b628f3f354 · inbound

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks cites this paper.

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-13T14:38:58.879673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T14:38:58.879673Z digest=sha256:1b0f3267c58f890d0ae7a980a700e8808e77b0b138c23343dca6ca66a4981df5

Observation 8658f980-8186-4615-b11b-930412589c82 · inbound

An AI Agent Execution Environment to Safeguard User Data cites this paper.

An AI Agent Execution Environment to Safeguard User Data Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 54

Resolution
verified exact
arxiv_id, observed 2026-05-11T13:11:05.891404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-10T02:14:40.639143Z digest=sha256:d1309e1277ce0dacf411b5d4f9e3e2b9518f81d5d6d6a6de874bb188507eb08e

Observation d42c1592-e1ca-42eb-8b34-26f2a22ef125 · inbound

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents cites this paper.

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 9

Resolution
metadata mismatch
arxiv_id, observed 2026-05-12T07:46:28.112736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-12T01:57:22.554881Z digest=sha256:43e90abef5a88c3c762a868309940c5bfb3eb71e143297ae9223fb32466793b2

Observation f3b68ddf-f963-4730-90a3-b625018c5aa8 · inbound

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents cites this paper.

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 9

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T13:45:45.437788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-30T22:52:54.684185Z digest=sha256:121fa02c1eb153430290b89d18f9b01eb3563fe090908a2a33f5f72692e04acd

Observation ec7cb2de-065f-4dac-865f-71bd54ed6d78 · inbound

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents cites this paper.

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-04T05:17:31.221017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T05:17:31.221017Z digest=sha256:836d3c1306bda838688de8f6a38d3ce9b036552a9d110cc51589a31d4fd63c83

Observation fde27398-675a-4de3-a358-7073ae7f9a9e · inbound

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection cites this paper.

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 22

Resolution
verified exact
arxiv_id, observed 2026-05-25T04:05:20.411461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-05-25T04:05:15.708438Z digest=sha256:6a2f7fef0018c4a673d03142164ec1d1f332323e9214e6d3d8080b5b838a1776

Observation c6f664a5-4dfe-4664-a750-3302e263781a · inbound

Prompt Injection Detection is Regime-Dependent: A Deployment-Aware Evaluation with Interpretable Structural Signals cites this paper.

Prompt Injection Detection is Regime-Dependent: A Deployment-Aware Evaluation with Interpretable Structural Signals Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 30

Resolution
verified exact
arxiv_id, observed 2026-06-29T18:43:50.228134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-29T18:41:03.566306Z digest=sha256:364a56233b2b3ea64123000384f9bae8b06aaf0d6c95b9e78c6ab463a9f8abcb

Observation a81e95ba-693a-486a-ac6d-7d77d24d1de0 · inbound

How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency cites this paper.

How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 13

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T14:13:30.554033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-29T06:53:48.841077Z digest=sha256:b67e3977946374aa28e374b85edc3d85a5abdf9e5c7b949ebe74558b209e8d94

Observation d21b7dbd-c8a7-487e-ae3a-4a75b3def877 · inbound

ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP cites this paper.

ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 22

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:54.253542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-26T04:07:14.506108Z digest=sha256:182967aef1f2571d7d6150f932d61033c50dc27b6f711d4a1a8a5ffb5ccee0ba

Observation c137ff90-863f-4cee-a111-6f3369f719e1 · inbound

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail cites this paper.

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-07-03T17:08:42.782288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-07-03T17:03:06.656045Z digest=sha256:d9fbdfeebed41c729434e71c7dd212c6a671c7faaa1ce2b125004a33687a38c5

Observation 73024db3-e914-4cc7-90d6-c919535614fb · inbound

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail cites this paper.

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-12T08:27:42.250470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-12T08:27:42.250470Z digest=sha256:be3f1fc2927b21fd736c3cf97b183ffb9173446291b586b54ad7409e16c08f19