Protecting systems, data and people as AI becomes part of everyday operations.
Статьи и видео публикуются на английском языке.
Обзор новостей, 5 мин чтения
GitHub code scanning can now flag indirect prompt injection, sensitive-data exposure and excessive agency in AI applications. Here is what the preview covers and how to use it without mistaking a scanner for a security programme.
AI security
Обзор стандарта, 2 мин чтения
ISO/IEC 42001 does not prescribe seven named documents; it requires controlled evidence that AI risks, responsibilities, and decisions are managed.
AI security
Видео
Europe didn't ban AI. It ranked the harm — and the high-risk band is where most real systems actually live.
AI security
Обзор стандарта, 2 мин чтения
The Cloud Security Alliance's trait-based approach maps agent behavior and architectural choices to concrete security risks and controls.
AI security
Обзор стандарта, 2 мин чтения
The OWASP AI Exchange provides a lifecycle map for moving from AI governance and threat analysis to testing, operations, and residual-risk decisions.
AI security
Обзор стандарта, 2 мин чтения
NIST's attack taxonomy helps security teams connect adversary goals, access, lifecycle stages, and mitigations across predictive and generative AI.
AI security
Обзор стандарта, 2 мин чтения
Microsoft's experience across 100 generative-AI products shows why testing must follow real system risks, not a generic attack checklist.
AI security
Обзор стандарта, 2 мин чтения
OWASP's 2025 list shows that securing an LLM application requires architecture, testing, and development controls around the model.
AI security
Обзор стандарта, 2 мин чтения
NIST's Generative AI Profile extends the AI RMF with concrete actions for governance, data provenance, testing, and incident disclosure.
AI security
Обзор стандарта, 2 мин чтения
BaFin's central point is simple: AI security has to cover the whole decision process, not just the model.
AI security
Обзор стандарта, 2 мин чтения
Google's SAIF implementation guide turns six security principles into an organizational process for designing, deploying, and operating AI safely.
AI security
Обзор стандарта, 2 мин чтения
Google's one-page SAIF summary provides a useful executive test for whether AI security covers architecture, operations, and business risk.
AI security
Обзор стандарта, 2 мин чтения
The NIST AI RMF gives organizations a lifecycle structure for connecting AI governance, assets, architecture, measurement, and risk treatment.
AI security
Следите там, где вам удобно читать. Подписка на рассылку не нужна.