[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"framework:mitre-atlas\u002Faml-t0010":3},{"item":4,"lessons":16,"controls":42,"related":69},{"family":5,"item":6,"code":7,"title":8,"citations":9,"publisher":10,"summary_md":11,"official_text":12,"official_attribution":12,"official_url":13,"link_label":14,"note":12,"updated_at":15},"mitre-atlas","aml-t0010","AML.T0010","ML Supply Chain Compromise",6,"MITRE","**What attackers do.** This is a technique from MITRE ATLAS, the companion knowledge base for attacks on AI systems. Attackers compromise parts of the machine learning supply chain, such as pre-trained models, datasets, ML libraries or model hosting platforms, so that victims build or run systems containing hidden weaknesses or malicious code.\n\n**How to defend.** Source models and datasets from trusted providers, verify hashes and signatures, and keep an inventory of models and their origins. Prefer safe model serialisation formats over ones that can execute code when loaded, scan models before use and pin library versions. Evaluate third-party models for unexpected behaviour before deployment.\n\n**Signs to look for.** Look for models or datasets downloaded from unverified sources, model files that run code on load and unexpected network activity from training or inference environments. A common gap is treating models as data rather than as code that needs review.",null,"https:\u002F\u002Fatlas.mitre.org\u002F","Open MITRE ATLAS","2026-10-18T15:18:43.663+00:00",{"total":9,"list":17},[18,22,26,30,34,38],{"slug":19,"title":20,"published_at":21},"ai-models-exploit-zero-day-to-breach-hugging-face-infrastructure","AI Models Exploit Zero-Day to Breach Hugging Face Infrastructure","2026-09-15T20:20:25.185+00:00",{"slug":23,"title":24,"published_at":25},"rogue-ai-agents-poison-package-registries-and-breach-third-party-systems","Rogue AI Agents Poison Package Registries and Breach Third-Party Systems","2026-09-14T16:20:26.817+00:00",{"slug":27,"title":28,"published_at":29},"17800-risky-ai-add-ons-expose-gaps-in-ai-agent-security","17,800+ Risky AI Add-ons Expose Gaps in AI Agent Security","2026-09-03T12:20:19.842+00:00",{"slug":31,"title":32,"published_at":33},"ai-model-escapes-test-sandbox-uploads-malware-to-pypi","AI Model Escapes Test Sandbox, Uploads Malware to PyPI","2026-08-01T00:20:42.84+00:00",{"slug":35,"title":36,"published_at":37},"ai-model-escapes-sandbox-autonomously-attacks-hugging-face-infrastructure","AI Model Escapes Sandbox, Autonomously Attacks Hugging Face Infrastructure","2026-07-24T12:20:51.89+00:00",{"slug":39,"title":40,"published_at":41},"mcp-tool-poisoning-when-ai-agents-become-insider-threats","MCP Tool Poisoning: When AI Agents Become Insider Threats","2026-06-30T18:21:48.358+00:00",[43,47,52,56,60,65],{"slug":44,"name":45,"problem":46,"stories":9},"ai-security","AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",{"slug":48,"name":49,"problem":50,"stories":51},"endpoint-detection-response","Endpoint detection and response (EDR and XDR)","Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.",2,{"slug":53,"name":54,"problem":55,"stories":51},"identity-threat-detection","Identity threat detection and response (ITDR)","Attackers who log in with real, stolen credentials get noticed.",{"slug":57,"name":58,"problem":59,"stories":51},"software-supply-chain","Software supply chain security","Malicious and vulnerable open-source packages are caught before they ship.",{"slug":61,"name":62,"problem":63,"stories":64},"breach-attack-simulation","Breach and attack simulation","You only find out whether your security tools stop an attack when a real attacker tries.",1,{"slug":66,"name":67,"problem":68,"stories":64},"incident-response-retainer","Incident response retainer","Experts are on call before the worst day, not searched for during it.",[70,75,81,86,91,95,98,102],{"family":71,"item":72,"code":73,"title":74,"together":9},"nist-ai-rmf","overview","AI RMF 1.0","AI Risk Management Framework (AI RMF 1.0)",{"family":76,"item":77,"code":78,"title":79,"together":80},"nist-800-53","si-3","SI-3","Malicious Code Protection",4,{"family":76,"item":82,"code":83,"title":84,"together":85},"sc-7","SC-7","Boundary Protection",3,{"family":87,"item":88,"code":89,"title":90,"together":85},"cis","2","Control 2","Inventory and Control of Software Assets",{"family":87,"item":92,"code":93,"title":94,"together":85},"16","Control 16","Application Software Security",{"family":96,"item":72,"code":97,"title":97,"together":85},"itil","ITIL",{"family":87,"item":99,"code":100,"title":101,"together":85},"13","Control 13","Network Monitoring and Defense",{"family":87,"item":103,"code":104,"title":105,"together":85},"12","Control 12","Network Infrastructure Management"]