Paper Citation Record · LEDGER

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

As of 8 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 2 inbound Pith citation observations for arXiv:2507.01321.

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

pith.paper-citation-record.v1
2507.01321 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:05:10.114257Z

measured 14 of 14 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T05:29:52.758898Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T05:31:07.650808Z

Reference resolution

12 of 12 outbound references displayed

verified exact0
verified fuzzy3
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b5416ae1-7151-4026-a1d8-1b7aa87c0ec0 · outbound

This paper cites The Closeness of In-Context Learning and Weight Shifting for Softmax Regression.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks The Closeness of In-Context Learning and Weight Shifting for Softmax Regression

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T21:05:10.365168Z

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 8fda8238-d536-42bc-b5bf-e3ddeb2b3706 · outbound

This paper cites Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:09.568138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cadb30a9-e97c-4e14-a65f-081e82e6490a · outbound

This paper cites Pre-trained Trojan Attacks for Visual Recognition.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks Pre-trained Trojan Attacks for Visual Recognition

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:09.655796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44ba6ce-276e-4fbc-bd64-4e03806efe78 · outbound

This paper cites D., Ng, A.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks D., Ng, A

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:10.663626Z

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 cb99f3ff-b32c-448b-b4c5-5476950f04dc · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:09.800071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6074e046-2986-40e7-95b2-0188448af411 · outbound

This paper cites Universal Backdoor Attacks Detection via Adaptive Adversarial Probe.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks Universal Backdoor Attacks Detection via Adaptive Adversarial Probe

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:09.921337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c79dfe34-b94d-4272-b26f-7690fbe23ae4 · outbound

This paper cites Backdooring instruction- tuned large language models with virtual prompt injec- tion.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks Backdooring instruction- tuned large language models with virtual prompt injec- tion

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:10.528394Z

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 53f68876-968c-4e4b-9105-c03019e3f982 · outbound

This paper cites Towards Robust Physical-world Backdoor Attacks on Lane Detection.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks Towards Robust Physical-world Backdoor Attacks on Lane Detection

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:10.114257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a940abab-913b-4266-895e-c9ba1acc9c89 · outbound

This paper cites GPT-NeoX-20B: An Open-Source Autoregressive Language Model.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks GPT-NeoX-20B: An Open-Source Autoregressive Language Model

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:09.164328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7a259a0-c9b8-4a6a-994f-f7ffbd1baab5 · outbound

This paper cites A survey on in- context learning.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks A survey on in- context learning

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:10.866330Z

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 2126c3dc-9a64-4c56-8ac6-1caa67e9e819 · outbound

This paper cites Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:09.469314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6d379d5-d134-4c04-8dd0-a36dd7d8e393 · outbound

This paper cites Adversarial Backdoor Defense in CLIP.

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks Adversarial Backdoor Defense in CLIP

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:09.316305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 42a59bec-4e81-4d54-83a6-bdfcc13ff736 · inbound

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models cites this paper.

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:05:49.264619Z

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 02bbecd6-08e6-4bba-85c1-a8ed865a5db2 · inbound

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting cites this paper.

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

Reference 122

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:31:07.653492Z

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.