AWS prescriptive-guidance documentation change
Summary
Added survey link, updated image path, removed markdown link formatting, and deleted architecture diagram reference
Security assessment
Changes include survey addition, image updates, and formatting changes. Security discussion about training data remains unchanged - modifications don't introduce new security content or address vulnerabilities.
Diff
diff --git a/prescriptive-guidance/latest/security-reference-architecture-generative-ai/gen-ai-model-inference.md b/prescriptive-guidance/latest/security-reference-architecture-generative-ai/gen-ai-model-inference.md index 7ababe02f..3305365f5 100644 --- a//prescriptive-guidance/latest/security-reference-architecture-generative-ai/gen-ai-model-inference.md +++ b//prescriptive-guidance/latest/security-reference-architecture-generative-ai/gen-ai-model-inference.md @@ -10,0 +11,3 @@ RationaleSecurity considerationsMulti-account architecture for AI workloadsDefen +Influence the future of the AWS Security Reference Architecture (AWS SRA) by taking a [short survey](https://amazonmr.au1.qualtrics.com/jfe/form/SV_e3XI1t37KMHU2ua). +--- + @@ -21 +24 @@ Organizations can also implement custom AI solutions using [Amazon SageMaker AI] -Custom models require enhanced monitoring for model drift, bias detection, and performance degradation that could indicate security issues or model compromise. When you customize FMs with your own training data (Scope 4) or train models from scratch (Scope 5), training data security becomes critical. Malicious or poisoned training data can compromise model behavior, introduce bias, or cause models to leak sensitive information during inference. For detailed guidance on securing model customization and training data, see [Capability 2](./gen-ai-rag.html). +Custom models require enhanced monitoring for model drift, bias detection, and performance degradation that could indicate security issues or model compromise. When you customize FMs with your own training data (Scope 4) or train models from scratch (Scope 5), training data security becomes critical. Malicious or poisoned training data can compromise model behavior, introduce bias, or cause models to leak sensitive information during inference. For detailed guidance on securing model customization and training data, see Capability 2. @@ -103 +106 @@ Organizations implementing AI at scale should adopt a multi-account strategy tha - + @@ -149,2 +151,0 @@ As shown in the following diagram, a defense-in-depth strategy implements securi - -