{"schema_version":"0.10.0","id":"LR-2026-0426","record_version":1,"title":"OpenAI reports Chinese state-linked operators used ChatGPT to plan influence and cyber campaigns","verification":{"human_verified":false,"method":"automated_gate","auto_verified":true,"score":49.6,"score_breakdown":{"source_authority":12.1,"independent_corroboration":7.0,"implicated_party_confirmed":0.0,"citation_integrity":14.0,"specificity":6.0,"completeness":4.16,"unhedged_language":3.85},"checks":{"schema_valid":true,"every_field_cited":true,"quotes_verbatim":true,"source_fetched":true,"distinct_incident":true,"dates_plausible":true,"sources_agree":true,"source_describes_incident":true,"severe_backed_by_source":true,"record_integrity":true,"eligible":true,"about_this_case":true},"gate_version":"gate-2026-10-18.7","cross_check_model":null,"cross_check_agreement":null,"duplicate_of":null,"verified_by":null,"verified_at":"2026-11-01","extraction_run_id":null,"evidence_level":{"level":"preliminary","reason":"1 report: Cyber Security News · subject to change","original_document":null,"reports_total":1,"reports_independent":1,"reports_derivative":0,"developing":false,"disputed":false,"rules_version":"evidence-2026-10-29.1","computed_at":"2026-11-01","history":[{"date":"2026-11-01","from_level":null,"to_level":"preliminary","reason":"1 report: Cyber Security News · subject to change"}]},"sources_hash":"bef345a11ed5b463edd626cc6e5c6c7a7c41aa24550c2290f221d834a3c04ba8"},"system":{"model_name":null,"model_version":null,"developer":"OpenAI","harness":null,"tools_granted":[],"permissions_scope":null,"autonomy_level":"unknown","guardrails_present":[],"deployment_context":"unknown","tier":null,"lifecycle_stage":null,"integration_type":null,"intended_use":null,"safeguard_state":null,"production_intended":null},"event":{"date_occurred":"2025-10-01","date_occurred_precision":"month","date_disclosed":"2026-02-26","incident_class":"harmful_output","failure_class":null,"agent_involved":null,"secondary_failure_classes":[],"trigger":"unknown","duration":null,"detection_method":"unknown","summary":"A ChatGPT account linked to an individual associated with Chinese law enforcement was used to plan and document covert cyberattack and influence campaigns, according to OpenAI’s February 2026 threat disruption report. In mid-October 2025 the user asked the model to help design a campaign targeting a Japanese politician, and the model refused. Despite that refusal, the operation went ahead, and the same user returned days later to polish a status report on its real-world implementation. OpenAI’s team confirmed the campaign’s footprint across several platforms. The operations reportedly spanned over 300 foreign social media platforms and involved thousands of fake accounts. The ChatGPT account was primarily used to edit and polish periodic status updates, while the operators used locally deployed models for monitoring and content creation.","tags":[],"date_detected":null,"near_miss":null,"root_cause":null,"root_cause_detail":null,"failure_class_detail":null,"responsible_party":null,"adversarial_actor":null,"input_provenance":null,"time_to_contain":null,"operations_paused":null,"remediation":null,"precursor_events":null,"primary_risk":"RK07","secondary_risks":["RK19"],"control_chain":[{"layer":"L1","party":"provider","party_name":"OpenAI","control_id":"D1","outcome":"held","reason":null,"quote":"OpenAI’s model refused to assist with this plan.","source_index":0,"reviewed":false}]},"impact":{"direct_loss_usd":null,"remediation_hours":null,"records_exposed":null,"third_parties_affected_count":null,"severity":"major","severity_because":"Major test: many third parties, a stated count of two or more affected parties. The source states the operations spanned over 300 foreign social media platforms.","harm_class":[],"affected_description":"Foreign dissidents, human rights groups, and foreign government officials","protected_class_involved":null,"data_categories_exposed":[],"loss_range_usd":null,"reversibility":null,"downstream_exposure_count":null},"evidence":{"sources":[{"url":"https://cybersecuritynews.com/openai-confirms-that-chinese-hackers-used-chatgpt/","publisher":"CyberSecurityNews","date":"2026-02-26","type":"press","title":"OpenAI Confirms that Chinese Hackers Used ChatGPT to Launch Cyberattacks - CyberSecurityNews","archived_url":null,"attachment":"first_report","independence":"independent"}],"per_field_confidence":{"system.developer":"C","event.date_occurred":"C","impact.affected_description":"C","event.incident_class":"D","impact.severity":"D","impact.severity_because":"D","event.primary_risk":"D","event.secondary_risks":"D","event.control_chain":"C","event.summary":"C","system.autonomy_level":"D","system.deployment_context":"D","event.trigger":"D","event.detection_method":"D","context.country":"D","event.date_disclosed":"D","context.denominator_available":"D"},"field_citations":{"system.developer":[{"source_index":0,"quote":"OpenAI has officially confirmed that a ChatGPT account linked to an individual associated with Chinese law enforcement was used to plan and document large-scale covert cyberattack campaigns."}],"event.date_occurred":[{"source_index":0,"quote":"OpenAI analysts identified a particularly alarming planning session in mid-October 2025, when the ChatGPT user asked the model to help design a covert influence campaign targeting Japanese politician Sanae Takaichi — who has since become Japan’s first female prime minister — after she publicly criticized human rights conditions in Inner Mongolia."}],"impact.affected_description":[{"source_index":0,"quote":"The targets were not limited to people inside China — they included foreign dissidents, human rights groups, and foreign government officials up to the highest levels of government."}],"event.incident_class":[{"source_index":0,"quote":"OpenAI has officially confirmed that a ChatGPT account linked to an individual associated with Chinese law enforcement was used to plan and document large-scale covert cyberattack campaigns."}],"impact.severity":[{"source_index":0,"quote":"The operations reportedly spanned over 300 foreign social media platforms, involved thousands of fake accounts, and were carried out by hundreds of human operators spread across multiple provinces in China."}],"impact.severity_because":[{"source_index":0,"quote":"The operations reportedly spanned over 300 foreign social media platforms, involved thousands of fake accounts, and were carried out by hundreds of human operators spread across multiple provinces in China."}],"event.control_chain":[{"source_index":0,"quote":"OpenAI’s model refused to assist with this plan."}],"event.summary":[{"source_index":0,"quote":"OpenAI has officially confirmed that a ChatGPT account linked to an individual associated with Chinese law enforcement was used to plan and document large-scale covert cyberattack campaigns."},{"source_index":0,"quote":"OpenAI’s model refused to assist with this plan."},{"source_index":0,"quote":"Despite that refusal, the operation did not stop there."},{"source_index":0,"quote":"The same user returned days later to polish a status report documenting the campaign’s real-world implementation — confirming that the attack had gone ahead without OpenAI’s platform."},{"source_index":0,"quote":"The operations reportedly spanned over 300 foreign social media platforms, involved thousands of fake accounts, and were carried out by hundreds of human operators spread across multiple provinces in China."},{"source_index":0,"quote":"The ChatGPT account was primarily used to edit and polish periodic status updates on ongoing campaigns, giving investigators a rare window into the inner workings of a Chinese state-affiliated disinformation machine."}]},"notes_on_gaps":"Only one press source (CyberSecurityNews) was provided; OpenAI's own threat report was not supplied, so details are second-hand. No model name, version, harness, tools, autonomy level, deployment context or lifecycle stage is stated. No failure_class is given because no autonomous agent was involved. date_disclosed is set to the month stated in the report title, not the article date. Trigger, root cause, responsible party, containment and remediation are not stated. No direct loss, record count, or exact third-party count is stated. Severity major is my judgement from the stated count of over 300 platforms. adversarial_actor external_attacker and detection_method human_review are judgements from the wording. [case created by the backfill: read by claude-haiku-5-5, backfill-2026-11-01.2, 2026-11-01; not yet reviewed] [2026-11-01: evidence level set: Preliminary (1 report: Cyber Security News · subject to change)]"},"context":{"industry":null,"org_size_band":null,"country":"unknown","denominator_available":false,"denominator":null,"related_incident_ids":[],"systemic_exposure":null,"shared_model_id":null,"upstream_incident_id":null,"incident_evidence":null,"regulatory":null,"coverage":null},"narrative":{"steps":[{"step":"doing","text":"A ChatGPT account was mainly used to edit and polish status updates on influence campaigns.","quote":"The ChatGPT account was primarily used to edit and polish periodic status updates on ongoing campaigns, giving investigators a rare window into the inner workings of a Chinese state-affiliated disinformation machine.","source_index":0,"grade":"C"},{"step":"went_wrong","text":"The user asked the model to help design a campaign against a Japanese politician. The model refused, and the operation went ahead anyway.","quote":"Despite that refusal, the operation did not stop there.","source_index":0,"grade":"C"}],"model":"claude-haiku-5-5","prompt_version":"backfill-2026-11-01.2","extracted_at":"2026-11-01","source_urls":["https://cybersecuritynews.com/openai-confirms-that-chinese-hackers-used-chatgpt/"]},"analysis":{"sections":{"timeline":[{"text":"OpenAI had first exposed the doxxing website revealscum.com as part of the Spamouflage network.","quote":"OpenAI further connected the operation to the doxxing website revealscum.com, which the company had first exposed as part of the Spamouflage network in May 2024.","source_index":0,"when":"2024-05"},{"text":"The ChatGPT user asked the model to help design a covert influence campaign targeting a Japanese politician; the model refused.","quote":"OpenAI analysts identified a particularly alarming planning session in mid-October 2025, when the ChatGPT user asked the model to help design a covert influence campaign targeting Japanese politician Sanae Takaichi — who has since become Japan’s first female prime minister — after she publicly criticized human rights conditions in Inner Mongolia.","source_index":0,"when":"2025-10"},{"text":"OpenAI published the findings in its February 2026 threat disruption report.","quote":"The revelation, published in OpenAI’s February 2026 threat disruption report, marks one of the most detailed public disclosures of how AI tools are being weaponized by state-linked actors to carry out coordinated influence operations and targeted harassment against dissidents, foreign officials, and critics of the Chinese Communist Party (CCP).","source_index":0,"when":"2026-02"}]},"model":"claude-haiku-5-5","prompt_version":"backfill-2026-11-01.2","extracted_at":"2026-11-01","source_urls":["https://cybersecuritynews.com/openai-confirms-that-chinese-hackers-used-chatgpt/"]}}