{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/flooding-spread-of-manipulated-knowledge-in","title":"Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities","arxiv_id":"2407.07791","date":"2024-07-10","proceeding":null,"authors":["Tianjie Ju","Yiting Wang","Xinbei Ma","Pengzhou Cheng","Haodong Zhao","Yulong Wang","Lifeng Liu","Jian Xie","Zhuosheng Zhang","Gongshen Liu"],"abstract":"The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation. However, the security implications of these LLM-based multi-agent systems have not been thoroughly investigated, particularly concerning the spread of manipulated knowledge. In this paper, we investigate this critical issue by constructing a detailed threat model and a comprehensive simulation environment that mirrors real-world multi-agent deployments in a trusted platform. Subsequently, we propose a novel two-stage attack method involving Persuasiveness Injection and Manipulated Knowledge Injection to systematically explore the potential for manipulated knowledge (i.e., counterfactual and toxic knowledge) spread without explicit prompt manipulation. Our method leverages the inherent vulnerabilities of LLMs in handling world knowledge, which can be exploited by attackers to unconsciously spread fabricated information. Through extensive experiments, we demonstrate that our attack method can successfully induce LLM-based agents to spread both counterfactual and toxic knowledge without degrading their foundational capabilities during agent communication. Furthermore, we show that these manipulations can persist through popular retrieval-augmented generation frameworks, where several benign agents store and retrieve manipulated chat histories for future interactions. This persistence indicates that even after the interaction has ended, the benign agents may continue to be influenced by manipulated knowledge. Our findings reveal significant security risks in LLM-based multi-agent systems, emphasizing the imperative need for robust defenses against manipulated knowledge spread, such as introducing ``guardian'' agents and advanced fact-checking tools.","url_abs":"https://arxiv.org/abs/2407.07791v2","url_pdf":"https://arxiv.org/pdf/2407.07791v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"flooding-spread-of-manipulated-knowledge-in","repo_url":"https://github.com/Jometeorie/KnowledgeSpread","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"persuasiveness","task_name":"Persuasiveness"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"},{"task_slug":"world-knowledge","task_name":"World Knowledge"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.07791","atlas_url":"https://app.syntology.ai/?focus=2407.07791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07791"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2407.07791"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2407.07791"},"call":"get_harvested_code_for_paper(arxiv_id=\"2407.07791\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2407.07791"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.07791\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.07791"},"call":"get_concepts_for_paper(arxiv_id=\"2407.07791\")"}],"by_repo":[{"repo":"Jometeorie/KnowledgeSpread","kind":"official","samples":9,"ran":6,"instrument":0,"unverified":3}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2407.07791.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2407.07791.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Jometeorie/KnowledgeSpread","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":3},"n_samples":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":9,"ran":6,"n_ran_checked":6,"n_instrument":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":6,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"23fedb033c4eb319","code_sha256_prefix":"23fedb033c4eb319","entry":"process_system_prompt","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/prompt.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"role_description:dict/0/?, prompt:str/0/str, is_edit:bool/0/bool","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"23fedb033c4eb319"}},{"code_sha256":"e505f066d4de6882","code_sha256_prefix":"e505f066d4de6882","entry":"process_system_prompt","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/prompt_defense.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/prompt_defense.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"role_description:dict/0/?, prompt:str/0/str, is_edit:bool/0/bool","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"e505f066d4de6882"}},{"code_sha256":"c27281e38be46bb2","code_sha256_prefix":"c27281e38be46bb2","entry":"prompt_template","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/baseline_easyedit.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/baseline_easyedit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"knowledge_for_edit:dict/0/?, question_type:str/0/str, model_type:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"c27281e38be46bb2"}},{"code_sha256":"c42bd9bc06461d7f","code_sha256_prefix":"c42bd9bc06461d7f","entry":"prompt_template","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/prompt.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prompt:str/0/str, full_history:list/1/dict, knowledge_for_edit:dict/0/?, role_description:dict/0/?, is_edit:bool/0/bool, model_type:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"c42bd9bc06461d7f"}},{"code_sha256":"799c1725a0ae3a17","code_sha256_prefix":"799c1725a0ae3a17","entry":"prompt_template","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/prompt_defense.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/prompt_defense.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prompt:str/0/str, full_history:list/1/dict, knowledge_for_edit:dict/0/?, role_description:dict/0/?, is_edit:bool/0/bool, model_type:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"799c1725a0ae3a17"}},{"code_sha256":"5e336051b1af74cb","code_sha256_prefix":"5e336051b1af74cb","entry":"prompt_template","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/prompt_supervision.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/prompt_supervision.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prompt:str/0/str, full_history:list/1/dict, knowledge_for_edit:dict/0/?, role_description:dict/0/?, is_edit:bool/0/bool, model_type:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"5e336051b1af74cb"}},{"code_sha256":"41f7fbef0bb0cb0f","code_sha256_prefix":"41f7fbef0bb0cb0f","entry":"generate_answer","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/baseline_easyedit.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/baseline_easyedit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/generate-answer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"41f7fbef0bb0cb0f"}},{"code_sha256":"c0e710682edfe8c0","code_sha256_prefix":"c0e710682edfe8c0","entry":"prompt_template","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/baseline_prompt_edit.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/baseline_prompt_edit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"c0e710682edfe8c0"}},{"code_sha256":"54d520992cd8e5bf","code_sha256_prefix":"54d520992cd8e5bf","entry":"rag_selection","repo":"Jometeorie/KnowledgeSpread","repo_kind":"official","path":"simulation/baseline_prompt_edit.py","file_url":"https://github.com/Jometeorie/KnowledgeSpread/blob/HEAD/simulation/baseline_prompt_edit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Jometeorie/KnowledgeSpread when it was checked","mcp_get_code":{"code_sha256":"54d520992cd8e5bf"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d223ed59e8a28cbd1a0d9fc27f5e69fe7acccd05f922644b3a2d7bc85f04bbe3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}