1 min. lasīšana
AI SecurityISO/IEC 42001 makes AI governance auditable
ISO/IEC 42001 does not prescribe seven named documents; it requires controlled evidence that AI risks, responsibilities, and decisions are managed.
Redakcionālā sērija
AI Security
Practical AI security: protecting systems, data, and people as AI becomes part of everyday operations.
Bloga ieraksti tiek publicēti tikai angļu valodā.
3 min. lasīšanaVideo
AI SecurityThe Risk-Based Blueprint inside the EU AI Act
Europe didn't ban AI. It ranked the harm — and the high-risk band is where most real systems actually live.
1 min. lasīšana
AI SecuritySecure AI agents by their traits, not their labels
The Cloud Security Alliance's trait-based approach maps agent behavior and architectural choices to concrete security risks and controls.
1 min. lasīšana
AI SecurityThe OWASP AI Exchange connects AI threats to controls
The OWASP AI Exchange provides a lifecycle map for moving from AI governance and threat analysis to testing, operations, and residual-risk decisions.
1 min. lasīšana
AI SecurityAdversarial machine learning needs a common language
NIST's attack taxonomy helps security teams connect adversary goals, access, lifecycle stages, and mitigations across predictive and generative AI.
1 min. lasīšana
AI SecurityRed teaming generative AI is a lifecycle discipline
Microsoft's experience across 100 generative-AI products shows why testing must follow real system risks, not a generic attack checklist.
1 min. lasīšana
AI SecurityThe OWASP LLM Top 10 is an application-security list
OWASP's 2025 list shows that securing an LLM application requires architecture, testing, and development controls around the model.
1 min. lasīšana
AI SecurityManaging generative-AI risk with the NIST profile
NIST's Generative AI Profile extends the AI RMF with concrete actions for governance, data provenance, testing, and incident disclosure.
1 min. lasīšana
AI SecurityAI security is governance in action
BaFin's central point is simple: AI security has to cover the whole decision process, not just the model.
1 min. lasīšana
AI SecurityPutting Google's Secure AI Framework into practice
Google's SAIF implementation guide turns six security principles into an organizational process for designing, deploying, and operating AI safely.
1 min. lasīšana
AI SecurityGoogle SAIF: six elements for secure AI
Google's one-page SAIF summary provides a useful executive test for whether AI security covers architecture, operations, and business risk.
2 min. lasīšana
AI SecurityNIST AI RMF: govern, map, measure, and manage
The NIST AI RMF gives organizations a lifecycle structure for connecting AI governance, assets, architecture, measurement, and risk treatment.