Paper Citation Record · LEDGER

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 19 inbound Pith citation observations for arXiv:2410.22770.

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

pith.paper-citation-record.v1
2410.22770 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 19 of 19 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 19 of 19 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:40:02.046929Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T15:59:56.705533Z

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 347b9855-fd2b-4166-9014-f50b5208fba5 · inbound

Detection Method for Prompt Injection by Integrating Pre-trained Model and Heuristic Feature Engineering cites this paper.

Detection Method for Prompt Injection by Integrating Pre-trained Model and Heuristic Feature Engineering InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T10:40:02.046929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b4a2a08-6a1f-44f4-8243-56230774416b · inbound

JavelinGuard: Low-Cost Transformer Architectures for LLM Security cites this paper.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.422926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d1e9437-1dc1-4d4b-8fbe-b90aeb12b0bd · inbound

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems cites this paper.

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:52.920395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20ed6250-4fe4-49a9-8648-c3bbcd5cfde3 · inbound

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling cites this paper.

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T22:01:57.303234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aacaf011-08ae-443a-bbec-441cec66951d · inbound

AgentWatcher: A Rule-based Prompt Injection Monitor cites this paper.

AgentWatcher: A Rule-based Prompt Injection Monitor InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T17:00:40.793545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43a33fbf-7458-4e60-a867-411c51cd5f03 · inbound

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation cites this paper.

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:10:59.673004Z

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.

Observation 1717068b-b9ec-47c5-ac04-c9fd8c3040da · inbound

Conjunctive Prompt Attacks in Multi-Agent LLM Systems cites this paper.

Conjunctive Prompt Attacks in Multi-Agent LLM Systems InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:17:37.659730Z

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.

Observation 43a1b4a0-ea53-4e14-9b25-9621e967ac39 · inbound

SafeAgent: A Runtime Protection Architecture for Agentic Systems cites this paper.

SafeAgent: A Runtime Protection Architecture for Agentic Systems InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:11:20.528650Z

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.

Observation 8fc45b19-0e07-4aa2-9b30-ebeceda40819 · inbound

MCP Pitfall Lab: Exposing Developer Pitfalls in MCP Tool Server Security under Multi-Vector Attacks cites this paper.

MCP Pitfall Lab: Exposing Developer Pitfalls in MCP Tool Server Security under Multi-Vector Attacks InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T14:31:07.935293Z

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.

Observation 695da77a-7ffb-48a2-af18-e81677200800 · inbound

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills cites this paper.

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:46:16.667903Z

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.

Observation 091bbcee-5dc8-4ce6-9393-8f9545cfef88 · inbound

Cross-Lingual Jailbreak Detection via Semantic Codebooks cites this paper.

Cross-Lingual Jailbreak Detection via Semantic Codebooks InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:46:20.461805Z

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.

Observation e75f430e-e303-4998-855b-cebf83364a4d · inbound

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection cites this paper.

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:56:13.711295Z

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.

Observation 32b24594-d718-48da-ab1b-50f31a7952a8 · inbound

Context-Aware Spear Phishing: Generative AI-Enabled Attacks Against Individuals via Public Social Media Data cites this paper.

Context-Aware Spear Phishing: Generative AI-Enabled Attacks Against Individuals via Public Social Media Data InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:52:05.373296Z

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.

Observation 24f60221-b2c9-48f0-9614-841e88f7e1af · 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 InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T18:43:50.533635Z

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.

Observation a46510d5-4881-484f-888c-80f14d8b7694 · inbound

Gate AI: LLM Security Benchmark Evaluation Methodology and Results cites this paper.

Gate AI: LLM Security Benchmark Evaluation Methodology and Results InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:46:19.192719Z

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.

Observation 7d0bc711-6e2f-4db4-9f43-205da7639bc2 · inbound

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models cites this paper.

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-02T17:47:18.106890Z

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.

Observation adf2fd2b-bb68-4f33-9e0e-78f69e983fd0 · inbound

Confidently Wrong: Severity-Aware Calibration of Prompt-Injection Detectors under Attack Shift cites this paper.

Confidently Wrong: Severity-Aware Calibration of Prompt-Injection Detectors under Attack Shift InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:29:44.071869Z

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.

Observation 4d75529e-afc7-4c10-a320-8b837f7e7327 · inbound

Verifying Intent and Harm: A Unified Defense Against LLM-Generated Threats cites this paper.

Verifying Intent and Harm: A Unified Defense Against LLM-Generated Threats InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T15:59:56.706982Z

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.

Observation 004175dd-d908-41ac-89ca-ea002c70cc3b · inbound

From Neural Intent to Cryptographic Authorization: Securing AI-Driven Enterprise Workflows cites this paper.

From Neural Intent to Cryptographic Authorization: Securing AI-Driven Enterprise Workflows InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T22:55:50.728137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.