Paper Citation Record · LEDGER

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning

As of 19 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 2 inbound Pith citation observations for arXiv:2505.11642.

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

pith.paper-citation-record.v1
2505.11642 v2

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:55:07.326283Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:57:29.612330Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy40
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b2d789a3-52f5-4b31-874e-095096258e16 · outbound

This paper cites Pal: Program-aided language models,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Pal: Program-aided language models,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.873475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c4e4f9c0-ad23-4029-9a1f-d10fd31fed6b · outbound

This paper cites Webgpt: Browser-assisted question-answering with human feedback,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Webgpt: Browser-assisted question-answering with human feedback,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.861970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f08c3f0a-db1b-4220-897b-440fb58db521 · outbound

This paper cites Language models are unsupervised multitask learners,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Language models are unsupervised multitask learners,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.850045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 95bfbe20-c473-4c34-9bfa-b1c66d1a956a · outbound

This paper cites Decodingtrust: A comprehensive assessment of trustworthiness in GPT models,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Decodingtrust: A comprehensive assessment of trustworthiness in GPT models,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.838248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0c636c3e-8c68-495f-914d-aa903da01c8d · outbound

This paper cites Backdoor attacks for in-context learning with language models,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Backdoor attacks for in-context learning with language models,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.824600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ac3a6b3b-4644-4e95-bd6c-358332f1a867 · outbound

This paper cites Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.811825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 77f7b391-7335-48b2-af70-52b45d61c906 · outbound

This paper cites Adver- sarial attacks and defenses in large language models: Old and new threats,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Adver- sarial attacks and defenses in large language models: Old and new threats,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.796655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 531d6b33-5977-4b33-9f3c-3a2bc1682d2a · outbound

This paper cites Backdoor threats from compromised foundation models to federated learning,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Backdoor threats from compromised foundation models to federated learning,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.783285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cea07a30-b9c9-4af8-8350-0ae455c7cb34 · outbound

This paper cites Unveiling backdoor risks brought by foundation models in heterogeneous federated learning,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Unveiling backdoor risks brought by foundation models in heterogeneous federated learning,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.771459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c994a1b7-268a-4bd7-b256-9b4558c7fe8a · outbound

This paper cites Onion: A simple and effective defense against textual backdoor attacks,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Onion: A simple and effective defense against textual backdoor attacks,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.760140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4649bdf0-fd0b-4869-820b-5512b675e5db · outbound

This paper cites Bddr: An effective defense against textual backdoor attacks,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Bddr: An effective defense against textual backdoor attacks,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.748349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d921fa28-e391-4087-b397-b5434f92bb5c · outbound

This paper cites Autodefense: Multi-agent llm defense against jailbreak attacks,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Autodefense: Multi-agent llm defense against jailbreak attacks,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.736465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6ddd9aec-c760-4e2d-b18e-3a1e597539a7 · outbound

This paper cites Prompt infection: Llm-to-llm prompt injection within multi-agent systems,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Prompt infection: Llm-to-llm prompt injection within multi-agent systems,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.723925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b3929e74-9bcc-4954-a2d1-cae8ee70e8d7 · outbound

This paper cites Red- teaming llm multi-agent systems via communication attacks,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Red- teaming llm multi-agent systems via communication attacks,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.709338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 66376a72-ab29-4d39-9f60-83e80530e720 · outbound

This paper cites Learning to reason with llms,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Learning to reason with llms,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.697761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3d1a3f08-3385-460d-a9f0-845dd27c6607 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.685947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cbb581fa-1274-46bf-ac84-7b996a59e361 · outbound

This paper cites Camel: Communicative agents for.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Camel: Communicative agents for

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.674346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 493e9364-d522-404c-ad77-aabbaa7e6037 · outbound

This paper cites Autogen: Enabling next- gen llm applications via multi-agent conversation framework,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Autogen: Enabling next- gen llm applications via multi-agent conversation framework,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.662117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0f6ae8ff-7af5-41de-97e3-627bee9f9597 · outbound

This paper cites Improving factuality and reasoning in language models through multiagent debate,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Improving factuality and reasoning in language models through multiagent debate,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.649965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c877b110-c8e1-4df4-9ca0-a0eabc3aeb54 · outbound

This paper cites Badnets: Identifying vulnerabilities in the machine learning model supply chain,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Badnets: Identifying vulnerabilities in the machine learning model supply chain,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.638225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 34dc12d3-da6e-4bda-94f3-ebe25a4e65de · outbound

This paper cites Badnl: Backdoor attacks against nlp models with semantic-preserving improvements,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Badnl: Backdoor attacks against nlp models with semantic-preserving improvements,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.626635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 04d4bda7-b20c-4766-a76a-e8eec46af098 · outbound

This paper cites Backdoor attacks on pre-trained models by layerwise weight poisoning,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Backdoor attacks on pre-trained models by layerwise weight poisoning,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.614488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d2a9ef21-7e1d-40dc-ab69-26523de54ce9 · outbound

This paper cites Prompt injection attack against llm-integrated applications,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Prompt injection attack against llm-integrated applications,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.600820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 59123b33-9caa-4537-ac92-70c4cb4c4f18 · outbound

This paper cites Multiagent collaboration attack: Investigating adversarial attacks in large language model collaborations via debate,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Multiagent collaboration attack: Investigating adversarial attacks in large language model collaborations via debate,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.588575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e15fc68e-04d1-4941-b505-be493a6be431 · outbound

This paper cites Watch out for your agents! investigating backdoor threats to llm-based agents,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Watch out for your agents! investigating backdoor threats to llm-based agents,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.577031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1aa1bb34-79a0-46b3-b342-01c0a271925f · outbound

This paper cites Stealthy and persistent unalign- ment on large language models via backdoor injections,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Stealthy and persistent unalign- ment on large language models via backdoor injections,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.564810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c2b3776e-2e3b-455b-a687-d51e7b808945 · outbound

This paper cites Chain-of- scrutiny: Detecting backdoor attacks for large language models,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Chain-of- scrutiny: Detecting backdoor attacks for large language models,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.552248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fd5667ad-8266-4e4d-b9dc-5232b3426a8c · outbound

This paper cites Badchain: Backdoor chain-of-thought prompt- ing for large language models,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Badchain: Backdoor chain-of-thought prompt- ing for large language models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.541246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a1b02cd0-be09-454d-b2cf-fef57cce0bf5 · outbound

This paper cites Measuring massive multitask language understanding,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Measuring massive multitask language understanding,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.529809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4d63be1c-c9f9-4b3e-84fb-644f2b448cdb · outbound

This paper cites Common- senseqa: A question answering challenge targeting common- sense knowledge,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Common- senseqa: A question answering challenge targeting common- sense knowledge,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.517692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ba9d9574-ec3b-48de-9c11-d39acebd7e41 · outbound

This paper cites Think you have solved question answering? try arc, the ai2 reasoning challenge,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Think you have solved question answering? try arc, the ai2 reasoning challenge,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.505335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fcc287ef-2512-4e15-906f-5a2bfcfa80a4 · outbound

This paper cites Hello gpt-4o,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Hello gpt-4o,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.491651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 61f9132c-7aa7-448b-99fe-9810016a0ce1 · outbound

This paper cites Introducing meta llama 3: The most capable openly available llm to date,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Introducing meta llama 3: The most capable openly available llm to date,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.479771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 12ab93b0-cf01-4131-b5d2-9213a809e6d0 · outbound

This paper cites Large language models are zero-shot reasoners,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Large language models are zero-shot reasoners,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.467815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d6c15214-a4c3-4ddb-b6b2-2f434ce63380 · outbound

This paper cites Automatic chain of thought prompting in large language models,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Automatic chain of thought prompting in large language models,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.453819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 71413506-7aaf-483a-a7d7-0d1493e6e865 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Chain-of-thought prompting elicits reasoning in large language models,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.440585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0ea81c0c-4e32-481d-a845-667ce1d9c461 · outbound

This paper cites an unresolved cited work.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:55:07.427661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a1ecd085-a495-4bae-a88a-a1705d3ad0ac · outbound

This paper cites an unresolved cited work.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:55:07.414825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 478cd15f-e2bf-4401-900e-7cf2d1e2207d · outbound

This paper cites Since the reasoning logically arrives at A (gravitational) being the correct answer, but the agent selects C (electrical), it indicates a significant error in their final choice.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Since the reasoning logically arrives at A (gravitational) being the correct answer, but the agent selects C (electrical), it indicates a significant error in their final choice

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.399844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation eb454a30-ace4-4d4d-b1e3-9f7bbc6bf019 · outbound

This paper cites gravitational: Correctly identified as the principal force that keeps planets in orbit.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning gravitational: Correctly identified as the principal force that keeps planets in orbit

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.386634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 287f6e61-acb8-4e98-9b18-e692fe7a173c · outbound

This paper cites gravitational,” which aligns perfectly with the correct understanding of the forces at play in celestial mechanics.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning gravitational,” which aligns perfectly with the correct understanding of the forces at play in celestial mechanics

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.374329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 94afa47e-80a5-4dc2-a70c-8966b4f81e13 · outbound

This paper cites Thus, there is a clear contradiction: the reasoning leads to the conclusion that ”A.

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning Thus, there is a clear contradiction: the reasoning leads to the conclusion that ”A

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:55:07.361288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation edacc772-bfb0-436b-94ec-b99525350db1 · inbound

SoK: Cybersecurity Assessment of Humanoid Ecosystem cites this paper.

SoK: Cybersecurity Assessment of Humanoid Ecosystem PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:29.612330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 166fa073-4e01-4383-93e6-481b571c755b · inbound

When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems cites this paper.

When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-14T03:26:15.676915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.