Paper Citation Record · LEDGER

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

As of 18 August 2026, this Paper Citation Record lists 90 of 90 outbound references and 7 inbound Pith citation observations for arXiv:2505.12442.

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

pith.paper-citation-record.v1
2505.12442 v3

Coverage vector

measured 90 of 90 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:38:59.032839Z

measured 97 of 97 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T22:07:42.219855Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-17T03:03:55.330037Z

Reference resolution

90 of 90 outbound references displayed

verified exact0
verified fuzzy45
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 94265197-348d-41eb-93a8-afb86d395450 · outbound

This paper cites Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:57.785099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 033415e6-20d8-4b9c-8171-e6d4742c70d4 · outbound

This paper cites Measuring and augmenting large language models for solving offensive security challenges,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Measuring and augmenting large language models for solving offensive security challenges,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:57.867901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e346d03-b100-4e9c-91d3-5023d2dc918f · outbound

This paper cites Causality-aided evaluation and explanation of large language model-based code generation,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Causality-aided evaluation and explanation of large language model-based code generation,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:57.877892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cad9222a-993a-478d-96ac-346c61a71380 · outbound

This paper cites Refining Decompiled C Code with Large Language Models.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Refining Decompiled C Code with Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:57.887403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9b765b8-9b04-4ed5-bd39-9df82748cd40 · outbound

This paper cites Navrepair: Node-type aware c/c++ code vulnerability repair,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Navrepair: Node-type aware c/c++ code vulnerability repair,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:57.896594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d27c44e4-15a9-440d-8eb3-fbce59e2cf0f · outbound

This paper cites Why Do Multi-Agent LLM Systems Fail?.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Why Do Multi-Agent LLM Systems Fail?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:57.905370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 566f7c14-dd4f-45e5-a92d-668f17ef5484 · outbound

This paper cites Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:57.911857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b1cee0-9d52-4801-8aca-6eac2b064cb4 · outbound

This paper cites Available: https://coze.com/.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Available: https://coze.com/

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.014179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 149a0fe5-63dc-4000-8407-a82ef788b2e4 · outbound

This paper cites Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.018872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 788ca2a5-eba8-4f7f-85ce-f88cbaf3482e · outbound

This paper cites Psysafe: A comprehensive framework for psychological-based attack, defense, and evaluation of multi-agent system safety,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Psysafe: A comprehensive framework for psychological-based attack, defense, and evaluation of multi-agent system safety,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.023702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fa947de-e582-436c-bfc0-f3f2a21d3bcc · outbound

This paper cites Flooding spread of manipulated knowledge in llm-based multi-agent communities,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Flooding spread of manipulated knowledge in llm-based multi-agent communities,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.028303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59ab72d9-c245-4ad1-8a02-06e0fe0f324f · outbound

This paper cites Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.038527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f554ebf9-172e-4ade-aeab-d7412b377830 · outbound

This paper cites Agents Under Siege: Breaking pragmatic multi-agent llm systems with optimized prompt attacks,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Agents Under Siege: Breaking pragmatic multi-agent llm systems with optimized prompt attacks,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.043385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dff674cb-6bbd-4616-a3e3-db0d5e7f2b3c · outbound

This paper cites Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.047903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0c989d3-20ba-44b3-9888-e6ca846d2cbc · outbound

This paper cites Pleak: Prompt leaking attacks against large language model applications,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Pleak: Prompt leaking attacks against large language model applications,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.052571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dbd7b50-26f1-459e-b67f-7e3a386d2432 · outbound

This paper cites Effective Prompt Extraction from Language Models.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Effective Prompt Extraction from Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.056705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebeb67aa-4a99-4115-94f7-d80ceab9d047 · outbound

This paper cites Privagent: Agentic-based red-teaming for llm privacy leakage,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Privagent: Agentic-based red-teaming for llm privacy leakage,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.177500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c11e66b6-1152-4433-8754-1face275d98e · outbound

This paper cites Chatbug: A common vulnerability of aligned llms induced by chat templates,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Chatbug: A common vulnerability of aligned llms induced by chat templates,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.344986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64670d1c-77a5-44b2-9aa8-8f8d543c286c · outbound

This paper cites LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.333823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a7ddb3c-2ff0-4efe-8fa4-b9fc5ec57ed4 · outbound

This paper cites Language Models are Few-Shot Learners.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Language Models are Few-Shot Learners

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.364122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9be1cff4-0cd6-4d87-be86-48e64b0ed551 · outbound

This paper cites Available: https://www.crewai.com/.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Available: https://www.crewai.com/

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.353530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2339572a-8873-4092-8b5b-522387d56fb1 · outbound

This paper cites Chatdev: Communicative agents for software development,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Chatdev: Communicative agents for software development,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.511489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f34aac86-0443-4416-99f7-9309b5182038 · outbound

This paper cites A survey on large language model based autonomous agents,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems A survey on large language model based autonomous agents,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.373218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44a7d73f-77af-42d1-96f9-8212998ea2b1 · outbound

This paper cites Tool learning with large language models: A survey,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Tool learning with large language models: A survey,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.693891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ced1cfad-5bd0-4999-8724-169370af6afc · outbound

This paper cites Metagpt: Meta programming for multi-agent collaborative framework,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Metagpt: Meta programming for multi-agent collaborative framework,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.708949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 741487f8-946b-4016-97db-3514acef40d1 · outbound

This paper cites On the resilience of llm-based multi-agent collaboration with faulty agents,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems On the resilience of llm-based multi-agent collaboration with faulty agents,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.662654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 12cb9e45-7e5c-4360-87c6-eac0600d1d31 · outbound

This paper cites Why do multi- agent llm systems fail?.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Why do multi- agent llm systems fail?

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.677999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 762b71f7-dfde-4d4f-819e-598e06263751 · outbound

This paper cites NetSafe: Exploring the Topological Safety of Multi-agent Networks.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems NetSafe: Exploring the Topological Safety of Multi-agent Networks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.590012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcc0b739-07a2-4fa1-9c27-2ead0c98e031 · outbound

This paper cites Scaling large language model-based multi-agent collaboration,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Scaling large language model-based multi-agent collaboration,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.647211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a3fc6c02-2080-464d-9f89-384e927b3766 · outbound

This paper cites Ignore previous prompt: Attack techniques for language models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Ignore previous prompt: Attack techniques for language models,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.617304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a98714c7-7b08-4124-9daa-8b5adfe0fd11 · outbound

This paper cites Stealing part of a production language model,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Stealing part of a production language model,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.632117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3d2f69f5-0aa6-4b11-9e2a-db4fa9ccb3af · outbound

This paper cites Struq: Defending against prompt injection with structured queries,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Struq: Defending against prompt injection with structured queries,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.586169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8b7df57e-3b50-45d0-b7dd-7ad85acaadcb · outbound

This paper cites RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.636039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b175b5c-883f-4b8a-8ca7-d1b12cce9cc7 · outbound

This paper cites When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.607813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc4e9fe1-de97-4d4c-86de-6ca54029a077 · outbound

This paper cites On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.738631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0582ef-c528-4a1c-8110-fd0b7ec62793 · outbound

This paper cites ToolBeHonest: A multi-level hallucination diagnostic benchmark for tool-augmented large language models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems ToolBeHonest: A multi-level hallucination diagnostic benchmark for tool-augmented large language models,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.553504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 60422f3e-bd32-4079-98e8-34dc2864af69 · outbound

This paper cites InFoBench: Evaluating instruction following ability in large language models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems InFoBench: Evaluating instruction following ability in large language models,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.569959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e02de8b-0ef6-4533-802f-0acb4fa38163 · outbound

This paper cites ChatDev: Communicative agents for software development,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems ChatDev: Communicative agents for software development,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.538451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aa7fe8c6-93fc-4a51-b52e-3dae5fd9b8a2 · outbound

This paper cites Finqa: A dataset of numerical reasoning over financial data,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Finqa: A dataset of numerical reasoning over financial data,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.523146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bf729d3d-4769-4c0d-acf8-b821fbcf8cc4 · outbound

This paper cites Autoagents: A framework for automatic agent generation,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Autoagents: A framework for automatic agent generation,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.747779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f36b4b4-cf68-44c8-b28e-1bab707d6bf8 · outbound

This paper cites Langchain.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Langchain

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.506037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3b4c9b8d-ea37-4b8d-a446-5a62257e0959 · outbound

This paper cites Llamaindex.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Llamaindex

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.488843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d0a98f25-b241-42d3-9ef6-b81f9441ebe5 · outbound

This paper cites What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.760949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7966798e-d60b-4760-b1f7-bebc29ffd6a4 · outbound

This paper cites Semantic diversity: A measure of semantic ambiguity based on variability in the contextual usage of words,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Semantic diversity: A measure of semantic ambiguity based on variability in the contextual usage of words,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.458148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b1ea756b-98cd-4f2f-8e24-184dfab9dcc2 · outbound

This paper cites Crewai examples.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Crewai examples

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.442392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b59094ac-0f20-49e0-9e78-3349a8048770 · outbound

This paper cites Topological complexity of motion planning,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Topological complexity of motion planning,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.473270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c085073e-33ed-4443-9e15-acb2fd2cb5a8 · outbound

This paper cites A survey of graph edit distance,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems A survey of graph edit distance,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.848301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140be8d2-c85a-4964-a34d-83515698bfd3 · outbound

This paper cites CCTEST: testing and repairing code completion systems,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems CCTEST: testing and repairing code completion systems,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.398699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3097500f-22a0-4640-a176-e58831f92449 · outbound

This paper cites Sentence transformers.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Sentence transformers

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.426337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3be42b69-e457-4e0a-963d-dee87cdc8fff · outbound

This paper cites Agentharm: A benchmark for measuring harmfulness of LLM agents,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Agentharm: A benchmark for measuring harmfulness of LLM agents,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.366980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 07306283-e6c7-40ff-bf47-be3aa283f78b · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Formalizing and benchmarking prompt injection attacks and defenses,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.351572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ad809e63-ec2e-4070-aa53-9c60a1c21821 · outbound

This paper cites Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.384062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 072b8190-6e18-4e2b-88de-a8d03de6b8b4 · outbound

This paper cites Llm-pbe: Assessing data privacy in large language models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Llm-pbe: Assessing data privacy in large language models,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.305750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cee3b992-e312-4c30-a4fa-37a05acb07ce · outbound

This paper cites The waterfall model in large- scale development,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems The waterfall model in large- scale development,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.289695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6737c5cf-7308-4f39-b3df-1545966c02e7 · outbound

This paper cites Large language model based multi-agents: A survey of progress and challenges,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Large language model based multi-agents: A survey of progress and challenges,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.890718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4230c1c4-ffb8-4216-b0cc-5d03c0566e54 · outbound

This paper cites Universal and transferable adversarial attacks on aligned language models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Universal and transferable adversarial attacks on aligned language models,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.877156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a020bdcd-4ce7-453c-9230-8a82d31e9764 · outbound

This paper cites React: Synergizing reasoning and acting in language models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems React: Synergizing reasoning and acting in language models,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.899608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfc3f235-8401-49bf-a57b-81fe5fd71fba · outbound

This paper cites Membership inference attacks against in-context learning,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Membership inference attacks against in-context learning,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.903891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002928c8-4bf0-4c2f-8abe-747200c0e8cd · outbound

This paper cites Optimization-based prompt injection attack to llm-as-a-judge,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Optimization-based prompt injection attack to llm-as-a-judge,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.907857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c51f1741-5da0-4d78-bf04-9f211c972f5c · outbound

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

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Chain-of-thought prompting elicits reasoning in large language models,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.895106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 715a7039-7324-47dc-b0a0-84d6b4e534be · outbound

This paper cites Sandwich defense.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Sandwich defense

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.253176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 75c2b94d-9c31-4da2-93f0-a9a71770a682 · outbound

This paper cites tiktoken.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems tiktoken

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.237686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4e7546c9-37c3-469b-aae9-a62ebc96903c · outbound

This paper cites Prompt Stealing Attacks Against Large Language Models.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Prompt Stealing Attacks Against Large Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.925899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45609da0-1038-4761-b774-1f3cd1e463c2 · outbound

This paper cites STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.911845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c9ed591-54ad-46ab-84a2-521bbe88806e · outbound

This paper cites SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.935856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d2ed037-2303-479c-bd95-7d8c28fe29f4 · outbound

This paper cites Stealing machine learning models via prediction {APIs},.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Stealing machine learning models via prediction {APIs},

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.206630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9bb1180d-eb52-4817-ba89-fa52e1a1880f · outbound

This paper cites Knockoff nets: Stealing functionality of black-box models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Knockoff nets: Stealing functionality of black-box models,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.189834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2a6287c1-5576-4fc3-ba30-9a93060438d7 · outbound

This paper cites Extracting prompts by inverting LLM outputs,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Extracting prompts by inverting LLM outputs,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.221914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fc87ca3a-c4f0-4044-be81-0eb0c47311af · outbound

This paper cites Practical black-box attacks against machine learning,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Practical black-box attacks against machine learning,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.954846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fc7bd1e-4173-4b9c-bec9-8c6c568ffe86 · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Scalable Extraction of Training Data from (Production) Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.958948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a63d4ac-ed50-4795-844b-f36cfbbb5ecc · outbound

This paper cites Differentiation-based ex- traction of proprietary data from fine-tuned llms,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Differentiation-based ex- traction of proprietary data from fine-tuned llms,

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.158446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5d074dfb-d7f1-47ca-82fc-1cb6914155d9 · outbound

This paper cites High accuracy and high fidelity extraction of neural networks,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems High accuracy and high fidelity extraction of neural networks,

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.173412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c37b6032-7fca-49fe-9dc0-f44184c29680 · outbound

This paper cites Split and merge: Aligning position biases in LLM-based evaluators,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Split and merge: Aligning position biases in LLM-based evaluators,

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.125278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8b035345-dd38-43c2-88dd-52edf36182d6 · outbound

This paper cites Decllm: Llm-augmented recompilable decom- pilation for enabling programmatic use of decompiled code,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Decllm: Llm-augmented recompilable decom- pilation for enabling programmatic use of decompiled code,

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.108285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6947dcdc-aca8-4892-b409-66c26adf3d1b · outbound

This paper cites Unleashing the power of compiler intermediate representation to enhance neural program embeddings,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Unleashing the power of compiler intermediate representation to enhance neural program embeddings,

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.090895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c7c60134-8a03-4cc3-b361-0320bb20ac3d · outbound

This paper cites Api-guided dataset synthesis to finetune large code models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Api-guided dataset synthesis to finetune large code models,

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.142692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation addc5b9f-bc15-4a40-857c-2d174c4ad720 · outbound

This paper cites Reef: A framework for collecting real-world vulnerabilities and fixes,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Reef: A framework for collecting real-world vulnerabilities and fixes,

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.058138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c6ce62bc-3a0a-4dfa-974a-8070dfcf68d3 · outbound

This paper cites On the feasibility of specialized ability stealing for large language code models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems On the feasibility of specialized ability stealing for large language code models,

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.041692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b47a667b-6f8b-4e0e-8cf0-e3d3ab61f81e · outbound

This paper cites Protecting intellectual property of large language model-based code generation apis via watermarks,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Protecting intellectual property of large language model-based code generation apis via watermarks,

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.024592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a9480f51-ff0e-4d05-a09f-ddaad096bc3b · outbound

This paper cites Beyond peft: Layer-wise optimization for more effective and efficient large code model tuning,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Beyond peft: Layer-wise optimization for more effective and efficient large code model tuning,

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.075087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c9085159-b754-4ad4-9d49-94fdecb9b28e · outbound

This paper cites Membership inference attacks from first principles,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Membership inference attacks from first principles,

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:38:59.995368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a8bc20c8-a2a6-4b5b-a42e-bf132994519e · outbound

This paper cites Enhanced membership inference attacks against machine learn- ing models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Enhanced membership inference attacks against machine learn- ing models,

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:38:59.977557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5bea3b06-de49-4305-ac12-43d39502793a · outbound

This paper cites Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:59.019029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f0be734-07bf-4892-b610-d60e1b2b789c · outbound

This paper cites Membership inference attacks against machine learning models,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Membership inference attacks against machine learning models,

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:59.005993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23225d3b-ad0d-4743-b2d2-6fc14b7c9f4e · outbound

This paper cites Membership inference attacks by exploiting loss trajectory,.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Membership inference attacks by exploiting loss trajectory,

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:38:59.949928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0793af9d-292f-4ed5-b495-4b812bc1efaa · outbound

This paper cites an unresolved cited work.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Unresolved cited work

Reference 89

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:38:59.931454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bff40caa-8515-4705-a0f9-553289155597 · outbound

This paper cites [[[” and ends with “]]].

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems [[[” and ends with “]]]

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:38:59.914590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3cef0f3e-5db7-4701-9929-a34e1bbd52c9 · outbound

This paper cites Available: https://www.usenix.org/conference/ usenixsecurity24/presentation/liu-yupei.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Available: https://www.usenix.org/conference/ usenixsecurity24/presentation/liu-yupei

Reference 1847

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.335410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d1de5068-34a0-48c3-83bd-06a6f0137a24 · outbound

This paper cites Available: https://openreview.net/forum?id= qiaRo 7Zmug.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Available: https://openreview.net/forum?id= qiaRo 7Zmug

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:39:00.602039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e0ef5508-92a7-4de7-a2b0-56b4c815f290 · outbound

This paper cites Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:58.032975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4dbd095f-2e00-48a7-a3de-9bad19a0d209 · inbound

Don't Trust Your Upstream: Exploiting LLM Multi-Agent System via Topology-Guided Adversarial Propagation cites this paper.

Don't Trust Your Upstream: Exploiting LLM Multi-Agent System via Topology-Guided Adversarial Propagation IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-17T03:03:55.332219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8b09601e-63ad-4bb1-a74d-27163ef11331 · inbound

Security Considerations for Multi-agent Systems cites this paper.

Security Considerations for Multi-agent Systems IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

Reference 172

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:15:55.960258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dd94921e-0323-4e9e-90fa-bb3f7f5c952c · inbound

Sequential Behavioral Watermarking for LLM Agents cites this paper.

Sequential Behavioral Watermarking for LLM Agents IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:47:04.109684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cb6184f3-595b-4919-91ff-184926ed9987 · inbound

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems cites this paper.

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:09.022536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 47734b4e-38e3-40cb-9e63-39dd71fec8af · inbound

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems cites this paper.

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T00:25:59.472346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1181928-a6dd-4bc4-81e2-21c2891f11cb · inbound

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems cites this paper.

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T04:17:02.531826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03059b16-f2ae-48d1-bbd0-fcca57eaf516 · inbound

Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity cites this paper.

Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T22:07:42.219855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.