Amazon Bedrock Guardrails announces the general availability of industry-leading image content filters
News
Amazon Bedrock Guardrails has announced the general availability of image content filters, providing advanced content safety for generative AI applications.
- Blocks up to 88% of harmful multi-modal content
- Offers configurable safeguards for detecting and blocking harmful content
- Supports content filtering across multiple categories like hate, violence, and sexual content
- Can be applied to foundation models hosted on Amazon Bedrock, self-hosted, and third-party models
- Provides capabilities like PII redaction and contextual grounding checks
- Currently available in US East, US West, Europe (Frankfurt), and Asia Pacific (Tokyo) regions
The solution eliminates the need for manual content moderation and helps customers build responsible AI applications with consistent safety controls.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Mar 28
2025
2025
Amazon Bedrock Guardrails image content filters provide industry-leading safeguards, helping customer block up to 88% of harmful multimodal content: Generally available today
Apr 23
2024
2024
Guardrails for Amazon Bedrock now available with new safety filters and privacy controls
Jun 24
2025
2025
Amazon Bedrock Guardrails announces tiers for content filters and denied topics
Dec 4
2024
2024
Amazon Bedrock Guardrails supports multimodal toxicity detection for image content (Preview)
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.