Skip to content
Submit incident
Organization/organizations/irregular

Irregular

12
Records
2026
Years covered
1
Category

Incident records12

Aug 2026AI companies warn of surge in AI-driven cyberattacksConfirmedSecurity and cyberattacksCBS NewsCNBCAol+2Aug 2026Meta AI model accesses unauthorized systems during security testingConfirmedSecurity and cyberattacksTVBSiThome OnlineAug 2026Meta AI model exploits security flaw, accesses external systems during testingUnder investigationSecurity and cyberattacksOlhar Digital - O futuro passa primeiro aquiuol.com.brAug 2026Meta AI model exploited security vulnerability during cybersecurity evaluationUnder investigationSecurity and cyberattacksreuters.comwashingtonpost.combleepingcomputer.comJul 2026OpenAI and Anthropic AI agents took unsanctioned actions during UK AISI cybersecurity evaluationsConfirmedSecurity and cyberattackswashingtonpost.comtransformernews.aiMay 2026Google Gemini accessed three real companies' protected systems during cybersecurity testConfirmedSecurity and cyberattackswsj.comMay 2026Google's Gemini AI autonomously hacks three companies during security testConfirmedSecurity and cyberattackshk.news.yahoo.comsetn.comApr 2026Anthropic Claude model hacked real website during security testConfirmedSecurity and cyberattacksreuters.comanthropic.comApr 2026AI agents escape testing environments, conduct cyberattacks without authorizationUnder investigationSecurity and cyberattacksiThome OnlineUDNFeb 2026AI Password Generators Found to Produce Predictable PasswordsReportedSecurity and cyberattacksTanjug News AgencySlobodna DalmacijaJan 2026Claude Opus 4.7 Gained Unauthorized Access to Real Production InfrastructureConfirmedSecurity and cyberattacksanthropic.comtransformernews.aiJan 2026Anthropic Claude Mythos 5 Scanned Targets and Uploaded Malicious Package During EvaluationConfirmedSecurity and cyberattacksanthropic.comtransformernews.ai