MManuela Schrittwieser·Oct 6Supply Chain Poisoning in AI/ML PipelinesNeuralStack | MS – AI Security Engineering Summary A modern ML system is assembled, not written. Training corpora are scraped or downloaded, weights are pulled from public hubs, and hundreds of trans16 min read·neuralstackms.tech55AJB
MManuela Schrittwieser·Aug 21Four AI Security Projects You Can Ship in a MonthWhy "one project per week" beats another certification8 min read·neuralstackms.tech72SD
MManuela Schrittwieser·Jul 27The Centaur Defense Model – Cooperative Defense Strategies Between Humans and AIThis article analyzes the “Centaur Defense Model,” an advanced security concept in which humans and artificial intelligence (AI) form a united front against malicious or infected systems. The core of6 min read·neuralstackms.tech41M
MManuela Schrittwieser·Jun 29Data Provenance, Lineage & Governance as AI Security ControlsNeuralStack | MS Tech Blog – Databases & Data Engineering in AI Security Engineering, Part 4 of 4 Governance Is Not Compliance Theatre The term "data governance" carries bureaucratic connotations in14 min read·neuralstackms.tech2
MManuela Schrittwieser·Jun 17RAG Under Fire: Retrieval Pipeline Vulnerabilities & Indirect Prompt InjectionNeuralStack | MS Tech Blog – Databases & Data Engineering in AI Security Engineering, Part 3 of 4 The Retrieval Pipeline as a Trust Boundary Retrieval-Augmented Generation (RAG) is now the dominant a14 min read·neuralstackms.tech
MManuela Schrittwieser·Jun 8The Hidden Attack Surface of Vector DatabasesNeuralStack | MS Tech Blog – Databases & Data Engineering in AI Security Engineering, Part 2 of 4 A New Storage Primitive, A New Threat Model Vector databases emerged as a distinct infrastructure cat12 min read·neuralstackms.tech
MManuela Schrittwieser·Jun 1Data Ingestion Attacks & AI Pipeline SecurityNeuralStack | MS Tech Blog – Databases & Data Engineering in AI Security Engineering, Part 1 of 4 The Pipeline Is the Attack Surface In classical application security, the perimeter is relatively wel10 min read·neuralstackms.tech
