AWS bedrock documentation change
Summary
Added 'DeepSeek' to list of models with non-removable request access in IAM policy documentation
Security assessment
Update expands documentation about security controls (IAM policies) for model access management but doesn't indicate a specific security vulnerability being addressed
Diff
diff --git a/bedrock/latest/userguide/security_iam_id-based-policy-examples.md b/bedrock/latest/userguide/security_iam_id-based-policy-examples.md index 4c4f61d27..b3f9e27ec 100644 --- a//bedrock/latest/userguide/security_iam_id-based-policy-examples.md +++ b//bedrock/latest/userguide/security_iam_id-based-policy-examples.md @@ -107 +107 @@ For the `aws-marketplace:Subscribe` action only, you can use the `aws-marketplac -You can't remove request access from the Amazon Titan, Amazon Nova, Mistral AI, and Meta Llama 3 Instruct models. You can prevent users from making inference calls to these models by using an IAM policy and specifying the model ID. For more information, see Deny access for inference of foundation models. +You can't remove request access from the Amazon Titan, Amazon Nova, DeepSeek, Mistral AI, and Meta Llama 3 Instruct models. You can prevent users from making inference calls to these models by using an IAM policy and specifying the model ID. For more information, see Deny access for inference of foundation models.