Paper Citation Record · LEDGER

Embedding-based classifiers can detect prompt injection attacks

As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 13 inbound Pith citation observations for arXiv:2410.22284.

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

pith.paper-citation-record.v1
2410.22284 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:51:58.722778Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T16:48:40.485860Z

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 04f5e35a-aceb-478d-8888-eb354d25f5aa · inbound

CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models cites this paper.

CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models Embedding-based classifiers can detect prompt injection attacks

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T14:51:58.722778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3b7a9a3-ed35-42f0-91de-d276a3752d30 · inbound

A Critical Evaluation of Defenses against Prompt Injection Attacks cites this paper.

A Critical Evaluation of Defenses against Prompt Injection Attacks Embedding-based classifiers can detect prompt injection attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:36:09.355811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8102041-b5ed-486b-a1a9-b473682b79f0 · inbound

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain cites this paper.

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain Embedding-based classifiers can detect prompt injection attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T10:44:10.367998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8cb91ea-23c5-4f3f-8bd6-ee69cbcd37ba · inbound

When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review cites this paper.

When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review Embedding-based classifiers can detect prompt injection attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T18:34:49.803058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abdb621b-8e2b-4036-b268-5d4fc8f11237 · inbound

Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs cites this paper.

Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs Embedding-based classifiers can detect prompt injection attacks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T09:53:26.376420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c497b8f6-1ad6-415c-9575-13ea48782b6e · inbound

Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning cites this paper.

Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning Embedding-based classifiers can detect prompt injection attacks

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-21T10:24:06.815203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8644cbe2-2eb7-47fd-b3de-881d339eb7ee · inbound

SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents cites this paper.

SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents Embedding-based classifiers can detect prompt injection attacks

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-12T00:06:17.911006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e563db05-895e-4cbf-933d-4168860992be · inbound

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

Cross-Lingual Jailbreak Detection via Semantic Codebooks Embedding-based classifiers can detect prompt injection attacks

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:46:21.951376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bee587d4-ef9f-4d8b-aafe-48b70d23e320 · inbound

SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation cites this paper.

SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation Embedding-based classifiers can detect prompt injection attacks

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:36:26.595693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5abd07eb-a11f-4a47-9963-acb62c6fef55 · inbound

PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations cites this paper.

PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations Embedding-based classifiers can detect prompt injection attacks

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:36:29.433801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 59b1276c-1746-44dc-943d-fd6922ba8370 · inbound

AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents cites this paper.

AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents Embedding-based classifiers can detect prompt injection attacks

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:48:40.487320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f44342e3-96a8-4a83-a8e6-7d7b55665f01 · inbound

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation cites this paper.

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation Embedding-based classifiers can detect prompt injection attacks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:39.957696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9134d8b-dd2b-4421-8603-ee389873bfdf · 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 Embedding-based classifiers can detect prompt injection attacks

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T22:55:49.367785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.